Compare commits
2 Commits
ef56e5dcdb
...
trt-replac
| Author | SHA1 | Date | |
|---|---|---|---|
| 68d695d81d | |||
| 65788be1b3 |
@@ -9,13 +9,7 @@
|
|||||||
"Bash(nvidia-smi:*)",
|
"Bash(nvidia-smi:*)",
|
||||||
"Bash(conda activate unifolm-wma)",
|
"Bash(conda activate unifolm-wma)",
|
||||||
"Bash(conda info:*)",
|
"Bash(conda info:*)",
|
||||||
"Bash(direnv allow:*)",
|
"Bash(direnv allow:*)"
|
||||||
"Bash(ls:*)",
|
|
||||||
"Bash(for scenario in unitree_g1_pack_camera unitree_z1_dual_arm_cleanup_pencils unitree_z1_dual_arm_stackbox unitree_z1_dual_arm_stackbox_v2 unitree_z1_stackbox)",
|
|
||||||
"Bash(do for case in case1 case2 case3 case4)",
|
|
||||||
"Bash(done)",
|
|
||||||
"Bash(chmod:*)",
|
|
||||||
"Bash(ln:*)"
|
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
2
.gitignore
vendored
2
.gitignore
vendored
@@ -132,3 +132,5 @@ Experiment/log
|
|||||||
|
|
||||||
*.0
|
*.0
|
||||||
ckpts/unifolm_wma_dual.ckpt.prepared.pt
|
ckpts/unifolm_wma_dual.ckpt.prepared.pt
|
||||||
|
trt_engines/video_backbone.engine
|
||||||
|
trt_engines/video_backbone.onnx
|
||||||
|
|||||||
208
record.md
Normal file
208
record.md
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
好，下面是完整的 decode 优化讲解。
|
||||||
|
|
||||||
|
---
|
||||||
|
背景：原始 decode 流程的问题
|
||||||
|
|
||||||
|
原始代码中，每轮迭代的 world model 交互会调用 image_guided_synthesis_sim_mode，内部对DDIM 采样得到的 latent 做全量 VAE decode：
|
||||||
|
|
||||||
|
# ddpms.py decode_core, perframe_ae=True
|
||||||
|
for index in range(z.shape[0]): # 逐帧循环，16帧就调16次
|
||||||
|
frame_z = 1. / self.scale_factor * z[index:index+1]
|
||||||
|
frame_result = self.first_stage_model.decode(frame_z)
|
||||||
|
results.append(frame_result)
|
||||||
|
|
||||||
|
假设 8 轮迭代、每轮 16 帧，WM 路径 decode 128 次，policy 路径再 decode 128 次，共 256 次 VAE decode。每次都是同步阻塞的。
|
||||||
|
|
||||||
|
decode 完的视频还会被逐轮写成 mp4 + tensorboard，产生大量磁盘 I/O。最后还要把所有轮的 decoded video 在内存中torch.cat
|
||||||
|
拼接，再写一次完整视频。
|
||||||
|
|
||||||
|
---
|
||||||
|
优化1：decode_video 开关——按需跳过 decode
|
||||||
|
|
||||||
|
文件： world_model_interaction.py函数 image_guided_synthesis_sim_mode
|
||||||
|
|
||||||
|
改动： 给函数加decode_video 参数（默认 False），返回值增加 raw samples：
|
||||||
|
|
||||||
|
def image_guided_synthesis_sim_mode(...,
|
||||||
|
decode_video: bool = False, # 新增
|
||||||
|
...) -> tuple[Tensor | None, Tensor, Tensor, Tensor | None]:
|
||||||
|
|
||||||
|
samples = None
|
||||||
|
if ddim_sampler is not None:
|
||||||
|
samples, actions, states, intermedia = ddim_sampler.sample(...)if decode_video: # 条件 decode
|
||||||
|
batch_images = model.decode_first_stage(samples)
|
||||||
|
batch_variants = batch_images
|
||||||
|
|
||||||
|
return batch_variants, actions, states, samples# 多返回 samples
|
||||||
|
|
||||||
|
调用侧：
|
||||||
|
- Policy 路径：由 CLI 参数 --fast_policy_no_decode 控制，只需要 action 时可跳过 decode
|
||||||
|
- WM 交互路径：传decode_video=False，只拿 raw latent
|
||||||
|
|
||||||
|
效果： WM 路径每轮省掉 16 帧全量 decode。
|
||||||
|
|
||||||
|
---
|
||||||
|
优化2：只decode observation 需要的帧
|
||||||
|
|
||||||
|
问题： WM 跳过了全量 decode，但下一轮的CLIP embedding 需要 pixel-space 图像做 observation。
|
||||||
|
|
||||||
|
改动： 只decode exe_steps 帧（通常 1帧），而不是全部 16 帧：
|
||||||
|
|
||||||
|
# WM 调用，不做全量 decode
|
||||||
|
pred_videos_1, _, pred_states, wm_samples = image_guided_synthesis_sim_mode(
|
||||||
|
..., decode_video=False)
|
||||||
|
|
||||||
|
# 只 decode exe_steps 帧给 observation
|
||||||
|
obs_pixels = model.decode_first_stage(
|
||||||
|
wm_samples[:, :, :args.exe_steps, :, :])
|
||||||
|
|
||||||
|
for idx in range(args.exe_steps):
|
||||||
|
observation = {
|
||||||
|
'observation.images.top':obs_pixels[0, :, idx:idx + 1].permute(1, 0, 2, 3),
|
||||||
|
...
|
||||||
|
}
|
||||||
|
cond_obs_queues = populate_queues(cond_obs_queues, observation)
|
||||||
|
|
||||||
|
关键细节： 必须逐帧填充 observation queue（idx:idx+1），不能全用最后一帧，否则 CLIP embedding 输入变了会影响精度。
|
||||||
|
|
||||||
|
效果： 每轮从 decode 16 帧降到 decode exe_steps 帧（省15 帧/轮）。
|
||||||
|
|
||||||
|
---
|
||||||
|
优化3：decode stream——GPU 上并行 decode 和 UNet
|
||||||
|
|
||||||
|
问题： 写入最终视频仍需要完整 segment 的 pixel，这部分 decode 还是要做。
|
||||||
|
|
||||||
|
思路： 用独立 CUDA stream 做 segment decode，和下一轮 UNet 推断在 GPU 上并行。
|
||||||
|
|
||||||
|
改动：
|
||||||
|
|
||||||
|
初始化：
|
||||||
|
decode_stream = torch.cuda.Stream(device=device)
|
||||||
|
pending_decode = None
|
||||||
|
|
||||||
|
循环尾部：
|
||||||
|
# 收集上一轮 decode 结果
|
||||||
|
if pending_decode is not None:
|
||||||
|
decode_stream.synchronize()
|
||||||
|
write_q.put(pending_decode.cpu())
|
||||||
|
pending_decode = None
|
||||||
|
|
||||||
|
# 在 decode stream 上启动当前轮 segment decode（不阻塞主线程）
|
||||||
|
latent_slice = wm_samples[:, :, :args.exe_steps]
|
||||||
|
decode_stream.wait_stream(torch.cuda.current_stream()) # 确保 latent 就绪
|
||||||
|
with torch.cuda.stream(decode_stream):
|
||||||
|
pending_decode = model.decode_first_stage(latent_slice)
|
||||||
|
# 主线程立即进入下一轮 UNet
|
||||||
|
|
||||||
|
循环结束后收集最后一轮：
|
||||||
|
if pending_decode is not None:
|
||||||
|
decode_stream.synchronize()
|
||||||
|
write_q.put(pending_decode.cpu())
|
||||||
|
|
||||||
|
原理： decode_stream.wait_stream() 建立 stream间依赖，确保 latent 产出后才开始 decode。两个 stream 的 kernel 可以被GPU
|
||||||
|
调度器交错执行。
|
||||||
|
|
||||||
|
效果： segment decode 时间被下一轮 UNet 推断掩盖。
|
||||||
|
|
||||||
|
---
|
||||||
|
优化4：Writer 进程——CPU 工作跨进程并行
|
||||||
|
|
||||||
|
问题： decode 完的tensor 需要转numpy + cv2 编码写盘，这是 CPU 密集型操作，Python GIL 限制线程并行。
|
||||||
|
|
||||||
|
改动：
|
||||||
|
|
||||||
|
辅助函数（主进程和子进程都能调用）：
|
||||||
|
def _video_tensor_to_frames(video: Tensor) -> np.ndarray:
|
||||||
|
video = torch.clamp(video.float(), -1., 1.)
|
||||||
|
n = video.shape[0]
|
||||||
|
video = video.permute(2, 0, 1, 3, 4)
|
||||||
|
frame_grids = [
|
||||||
|
torchvision.utils.make_grid(f, nrow=int(n), padding=0) for f in video
|
||||||
|
]
|
||||||
|
grid = torch.stack(frame_grids, dim=0)
|
||||||
|
grid = ((grid + 1.0) / 2.0 * 255).to(torch.uint8).permute(0, 2, 3, 1)
|
||||||
|
return grid.numpy()[:, :, :, ::-1] # RGB → BGR
|
||||||
|
|
||||||
|
Writer 进程：
|
||||||
|
def _video_writer_process(q: mp.Queue, filename: str, fps: int):
|
||||||
|
vwriter = None
|
||||||
|
while True:
|
||||||
|
item = q.get()
|
||||||
|
if item is None: # sentinel，退出
|
||||||
|
break
|
||||||
|
frames = _video_tensor_to_frames(item)
|
||||||
|
if vwriter is None:
|
||||||
|
h, w = frames.shape[1], frames.shape[2]
|
||||||
|
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
|
||||||
|
vwriter = cv2.VideoWriter(filename, fourcc, fps, (w, h))
|
||||||
|
for f in frames:
|
||||||
|
vwriter.write(f)
|
||||||
|
if vwriter is not None:
|
||||||
|
vwriter.release()
|
||||||
|
|
||||||
|
主进程启动 writer：
|
||||||
|
write_q = mp.Queue()
|
||||||
|
writer_proc = mp.Process(target=_video_writer_process,
|
||||||
|
args=(write_q, sample_full_video_file, args.save_fps))
|
||||||
|
writer_proc.start()
|
||||||
|
|
||||||
|
主进程通过 write_q.put(tensor.cpu()) 发送数据，循环结束发None sentinel 并join()。
|
||||||
|
|
||||||
|
效果：
|
||||||
|
- tensor→numpy 转换和cv2 编码不占主进程 CPU 时间
|
||||||
|
- 不受 GIL 限制
|
||||||
|
- cv2.VideoWriter 增量写入，不攒内存，不做最终 torch.cat
|
||||||
|
- Queue 自带背压，writer 处理不过来时 put 自然阻塞，不会 OOM
|
||||||
|
|
||||||
|
---
|
||||||
|
同时删除的冗余 I/O
|
||||||
|
|
||||||
|
- 每轮迭代的 WM 中间tensorboard log（log_to_tensorboard_async）
|
||||||
|
- 每轮迭代的 WM 中间 mp4（save_results_async）
|
||||||
|
- 每轮迭代的 policy 中间 mp4
|
||||||
|
- 最终的 torch.cat + 一次性 save_results_async 写完整视频
|
||||||
|
|
||||||
|
---
|
||||||
|
总结：优化前后对比
|
||||||
|
|
||||||
|
┌─────────────────────┬────────────────────────┬───────────────────────────┐
|
||||||
|
│ │ 原始 │ 优化后 │
|
||||||
|
├─────────────────────┼────────────────────────┼───────────────────────────┤
|
||||||
|
│ WM decode帧数/轮 │ 16 │ exe_steps（通常1） │
|
||||||
|
├─────────────────────┼────────────────────────┼───────────────────────────┤
|
||||||
|
│ segment decode 阻塞 │ 同步阻塞主线程 │ decode stream，GPU并行 │
|
||||||
|
├─────────────────────┼────────────────────────┼───────────────────────────┤
|
||||||
|
│ tensor→numpy+写盘 │ 主线程同步/线程池(GIL) │ 独立进程，无GIL │
|
||||||
|
├─────────────────────┼────────────────────────┼───────────────────────────┤
|
||||||
|
│ 视频写入方式 │ 攒内存→cat→一次写 │ cv2增量追加写 │
|
||||||
|
├─────────────────────┼────────────────────────┼───────────────────────────┤
|
||||||
|
│ 中间I/O │ 每轮2×mp4+2×tb │ 无 │
|
||||||
|
├─────────────────────┼────────────────────────┼───────────────────────────┤
|
||||||
|
│ 内存占用 │ 随迭代数线性增长 │ 恒定（不攒decoded video） │
|
||||||
|
└─────────────────────┴────────────────────────┴───────────────────────────┘
|
||||||
|
|
||||||
|
✻ Cooked for 1m 31s
|
||||||
|
|
||||||
|
❯ 目前哪些优化是默认开启的
|
||||||
|
|
||||||
|
● 让我检查各个优化的开关状态。
|
||||||
|
|
||||||
|
● Searched for 2 patterns (ctrl+o to expand)
|
||||||
|
|
||||||
|
● 当前各优化的默认状态：
|
||||||
|
|
||||||
|
┌───────────────────────────────────┬────────────┬────────────────────────────────────────────────────────┐
|
||||||
|
│ 优化 │ 默认开启？ │ 控制方式 │
|
||||||
|
├───────────────────────────────────┼────────────┼────────────────────────────────────────────────────────┤
|
||||||
|
│ WM路径跳过全量decode │ ✅ 是 │ 硬编码 decode_video=False（789行） │
|
||||||
|
├───────────────────────────────────┼────────────┼────────────────────────────────────────────────────────┤
|
||||||
|
│ 只decode exe_steps帧给observation │ ✅ 是 │ 无开关，直接生效（792行） │
|
||||||
|
├───────────────────────────────────┼────────────┼────────────────────────────────────────────────────────┤
|
||||||
|
│ decode stream GPU并行 │ ✅ 是 │ 无开关，直接生效（824-827行） │
|
||||||
|
├───────────────────────────────────┼────────────┼────────────────────────────────────────────────────────┤
|
||||||
|
│ Writer进程增量写盘 │ ✅ 是 │ 无开关，直接生效（672-675行） │
|
||||||
|
├───────────────────────────────────┼────────────┼────────────────────────────────────────────────────────┤
|
||||||
|
│ 删除中间wm mp4/tb保存 │ ✅ 是 │ 代码已删除 │
|
||||||
|
├───────────────────────────────────┼────────────┼────────────────────────────────────────────────────────┤
|
||||||
|
│ Policy路径跳过decode │ ❌ 否 │ 需传--fast_policy_no_decode（默认False，即默认decode） │
|
||||||
|
└───────────────────────────────────┴────────────┴────────────────────────────────────────────────────────┘
|
||||||
File diff suppressed because it is too large
Load Diff
@@ -1,37 +0,0 @@
|
|||||||
2026-02-11 17:34:29.188470: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 17:34:29.238296: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 17:34:29.238342: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 17:34:29.239649: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 17:34:29.247152: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 17:34:30.172640: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
File diff suppressed because it is too large
Load Diff
504
run_all_cases_20260218_190150.log
Normal file
504
run_all_cases_20260218_190150.log
Normal file
@@ -0,0 +1,504 @@
|
|||||||
|
2026-02-18 19:01:56.891895: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
|
2026-02-18 19:01:56.940243: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
|
2026-02-18 19:01:56.940285: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
|
2026-02-18 19:01:56.941395: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
|
2026-02-18 19:01:56.948327: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
|
2026-02-18 19:01:57.870809: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
|
Global seed set to 123
|
||||||
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
|
>>> Prepared model loaded.
|
||||||
|
INFO:root:***** Configing Data *****
|
||||||
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
|
>>> unitree_z1_stackbox: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
||||||
|
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
||||||
|
>>> unitree_g1_pack_camera: data stats loaded.
|
||||||
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
|
>>> Dataset is successfully loaded ...
|
||||||
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
|
>>> Generate 16 frames under each generation ...
|
||||||
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-19:02:10] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
|
9%|▉ | 1/11 [00:17<02:51, 17.15s/it]>>> Step 0: generating actions ...
|
||||||
|
>>> Step 0: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 1: generating actions ...
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
|
||||||
|
18%|█▊ | 2/11 [00:33<02:31, 16.87s/it]
|
||||||
|
27%|██▋ | 3/11 [00:50<02:14, 16.76s/it]
|
||||||
|
36%|███▋ | 4/11 [01:07<01:57, 16.81s/it]
|
||||||
|
45%|████▌ | 5/11 [01:24<01:41, 16.85s/it]
|
||||||
|
55%|█████▍ | 6/11 [01:41<01:24, 16.82s/it]
|
||||||
|
64%|██████▎ | 7/11 [01:57<01:07, 16.82s/it]
|
||||||
|
73%|███████▎ | 8/11 [02:14<00:50, 16.83s/it]
|
||||||
|
82%|████████▏ | 9/11 [02:31<00:33, 16.80s/it]
|
||||||
|
91%|█████████ | 10/11 [02:48<00:16, 16.81s/it]
|
||||||
|
100%|██████████| 11/11 [03:05<00:00, 16.81s/it]
|
||||||
|
100%|██████████| 11/11 [03:05<00:00, 16.83s/it]
|
||||||
|
>>> Step 1: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 2: generating actions ...
|
||||||
|
>>> Step 2: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 3: generating actions ...
|
||||||
|
>>> Step 3: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 4: generating actions ...
|
||||||
|
>>> Step 4: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 5: generating actions ...
|
||||||
|
>>> Step 5: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 6: generating actions ...
|
||||||
|
>>> Step 6: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 7: generating actions ...
|
||||||
|
>>> Step 7: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 8: generating actions ...
|
||||||
|
>>> Step 8: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 9: generating actions ...
|
||||||
|
>>> Step 9: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 10: generating actions ...
|
||||||
|
>>> Step 10: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
|
||||||
|
real 3m49.072s
|
||||||
|
user 4m16.055s
|
||||||
|
sys 0m44.636s
|
||||||
|
2026-02-18 19:05:45.956647: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
|
2026-02-18 19:05:46.004149: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
|
2026-02-18 19:05:46.004193: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
|
2026-02-18 19:05:46.005265: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
|
2026-02-18 19:05:46.012074: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
|
2026-02-18 19:05:46.932966: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
|
Global seed set to 123
|
||||||
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
|
>>> Prepared model loaded.
|
||||||
|
INFO:root:***** Configing Data *****
|
||||||
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
|
>>> unitree_z1_stackbox: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
||||||
|
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
||||||
|
>>> unitree_g1_pack_camera: data stats loaded.
|
||||||
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
|
>>> Dataset is successfully loaded ...
|
||||||
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
|
>>> Generate 16 frames under each generation ...
|
||||||
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-19:05:59] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
|
9%|▉ | 1/11 [00:16<02:47, 16.71s/it]>>> Step 0: generating actions ...
|
||||||
|
>>> Step 0: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 1: generating actions ...
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
|
||||||
|
18%|█▊ | 2/11 [00:33<02:30, 16.75s/it]
|
||||||
|
27%|██▋ | 3/11 [00:50<02:15, 16.91s/it]
|
||||||
|
36%|███▋ | 4/11 [01:07<01:59, 17.02s/it]
|
||||||
|
45%|████▌ | 5/11 [01:24<01:41, 16.98s/it]
|
||||||
|
55%|█████▍ | 6/11 [01:41<01:24, 16.94s/it]
|
||||||
|
64%|██████▎ | 7/11 [01:58<01:07, 16.90s/it]
|
||||||
|
73%|███████▎ | 8/11 [02:15<00:50, 16.83s/it]
|
||||||
|
82%|████████▏ | 9/11 [02:31<00:33, 16.80s/it]
|
||||||
|
91%|█████████ | 10/11 [02:49<00:16, 16.94s/it]
|
||||||
|
100%|██████████| 11/11 [03:06<00:00, 16.97s/it]
|
||||||
|
100%|██████████| 11/11 [03:06<00:00, 16.91s/it]
|
||||||
|
>>> Step 1: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 2: generating actions ...
|
||||||
|
>>> Step 2: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 3: generating actions ...
|
||||||
|
>>> Step 3: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 4: generating actions ...
|
||||||
|
>>> Step 4: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 5: generating actions ...
|
||||||
|
>>> Step 5: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 6: generating actions ...
|
||||||
|
>>> Step 6: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 7: generating actions ...
|
||||||
|
>>> Step 7: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 8: generating actions ...
|
||||||
|
>>> Step 8: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 9: generating actions ...
|
||||||
|
>>> Step 9: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 10: generating actions ...
|
||||||
|
>>> Step 10: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
|
||||||
|
real 3m49.162s
|
||||||
|
user 4m12.814s
|
||||||
|
sys 0m45.565s
|
||||||
|
2026-02-18 19:09:35.113634: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
|
2026-02-18 19:09:35.161428: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
|
2026-02-18 19:09:35.161474: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
|
2026-02-18 19:09:35.162551: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
|
2026-02-18 19:09:35.169325: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
|
2026-02-18 19:09:36.089250: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
|
Global seed set to 123
|
||||||
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
|
>>> Prepared model loaded.
|
||||||
|
INFO:root:***** Configing Data *****
|
||||||
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
|
>>> unitree_z1_stackbox: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
||||||
|
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
||||||
|
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
||||||
|
>>> unitree_g1_pack_camera: data stats loaded.
|
||||||
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
|
>>> Dataset is successfully loaded ...
|
||||||
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
|
>>> Generate 16 frames under each generation ...
|
||||||
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-19:09:49] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
|
9%|▉ | 1/11 [00:16<02:45, 16.53s/it]>>> Step 0: generating actions ...
|
||||||
|
>>> Step 0: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 1: generating actions ...
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
0
run_all_psnr.sh
Executable file → Normal file
0
run_all_psnr.sh
Executable file → Normal file
@@ -450,9 +450,8 @@ def image_guided_synthesis_sim_mode(
|
|||||||
|
|
||||||
img = observation['observation.images.top'].permute(0, 2, 1, 3, 4)
|
img = observation['observation.images.top'].permute(0, 2, 1, 3, 4)
|
||||||
cond_img = rearrange(img, 'b o c h w -> (b o) c h w')[-1:]
|
cond_img = rearrange(img, 'b o c h w -> (b o) c h w')[-1:]
|
||||||
with torch.cuda.amp.autocast(dtype=torch.float16):
|
cond_img_emb = model.embedder(cond_img)
|
||||||
cond_img_emb = model.embedder(cond_img)
|
cond_img_emb = model.image_proj_model(cond_img_emb)
|
||||||
cond_img_emb = model.image_proj_model(cond_img_emb)
|
|
||||||
|
|
||||||
if model.model.conditioning_key == 'hybrid':
|
if model.model.conditioning_key == 'hybrid':
|
||||||
z = get_latent_z(model, img.permute(0, 2, 1, 3, 4))
|
z = get_latent_z(model, img.permute(0, 2, 1, 3, 4))
|
||||||
@@ -466,12 +465,11 @@ def image_guided_synthesis_sim_mode(
|
|||||||
prompts = [""] * batch_size
|
prompts = [""] * batch_size
|
||||||
cond_ins_emb = model.get_learned_conditioning(prompts)
|
cond_ins_emb = model.get_learned_conditioning(prompts)
|
||||||
|
|
||||||
with torch.cuda.amp.autocast(dtype=torch.float16):
|
cond_state_emb = model.state_projector(observation['observation.state'])
|
||||||
cond_state_emb = model.state_projector(observation['observation.state'])
|
cond_state_emb = cond_state_emb + model.agent_state_pos_emb
|
||||||
cond_state_emb = cond_state_emb + model.agent_state_pos_emb
|
|
||||||
|
|
||||||
cond_action_emb = model.action_projector(observation['action'])
|
cond_action_emb = model.action_projector(observation['action'])
|
||||||
cond_action_emb = cond_action_emb + model.agent_action_pos_emb
|
cond_action_emb = cond_action_emb + model.agent_action_pos_emb
|
||||||
|
|
||||||
if not sim_mode:
|
if not sim_mode:
|
||||||
cond_action_emb = torch.zeros_like(cond_action_emb)
|
cond_action_emb = torch.zeros_like(cond_action_emb)
|
||||||
@@ -494,7 +492,6 @@ def image_guided_synthesis_sim_mode(
|
|||||||
cond_mask = None
|
cond_mask = None
|
||||||
cond_z0 = None
|
cond_z0 = None
|
||||||
batch_variants = None
|
batch_variants = None
|
||||||
samples = None
|
|
||||||
if ddim_sampler is not None:
|
if ddim_sampler is not None:
|
||||||
samples, actions, states, intermedia = ddim_sampler.sample(
|
samples, actions, states, intermedia = ddim_sampler.sample(
|
||||||
S=ddim_steps,
|
S=ddim_steps,
|
||||||
@@ -518,7 +515,7 @@ def image_guided_synthesis_sim_mode(
|
|||||||
batch_images = model.decode_first_stage(samples)
|
batch_images = model.decode_first_stage(samples)
|
||||||
batch_variants = batch_images
|
batch_variants = batch_images
|
||||||
|
|
||||||
return batch_variants, actions, states, samples
|
return batch_variants, actions, states
|
||||||
|
|
||||||
|
|
||||||
def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
||||||
@@ -574,22 +571,6 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
|||||||
torch.save(model, prepared_path)
|
torch.save(model, prepared_path)
|
||||||
print(f">>> Prepared model saved ({os.path.getsize(prepared_path) / 1024**3:.1f} GB).")
|
print(f">>> Prepared model saved ({os.path.getsize(prepared_path) / 1024**3:.1f} GB).")
|
||||||
|
|
||||||
# ---- FP16: convert diffusion backbone + conditioning modules ----
|
|
||||||
model.model.to(torch.float16)
|
|
||||||
model.model.diffusion_model.dtype = torch.float16
|
|
||||||
print(">>> Diffusion backbone (model.model) converted to FP16.")
|
|
||||||
|
|
||||||
# Projectors / MLP → FP16
|
|
||||||
model.image_proj_model.half()
|
|
||||||
model.state_projector.half()
|
|
||||||
model.action_projector.half()
|
|
||||||
print(">>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.")
|
|
||||||
|
|
||||||
# Text/image encoders → FP16
|
|
||||||
model.cond_stage_model.half()
|
|
||||||
model.embedder.half()
|
|
||||||
print(">>> Encoders (cond_stage_model, embedder) converted to FP16.")
|
|
||||||
|
|
||||||
# Build normalizer (always needed, independent of model loading path)
|
# Build normalizer (always needed, independent of model loading path)
|
||||||
logging.info("***** Configing Data *****")
|
logging.info("***** Configing Data *****")
|
||||||
data = instantiate_from_config(config.data)
|
data = instantiate_from_config(config.data)
|
||||||
@@ -604,6 +585,11 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
|||||||
if isinstance(m, CrossAttention) and m.fuse_kv())
|
if isinstance(m, CrossAttention) and m.fuse_kv())
|
||||||
print(f" ✓ KV fused: {kv_count} attention layers")
|
print(f" ✓ KV fused: {kv_count} attention layers")
|
||||||
|
|
||||||
|
# Load TRT backbone if engine exists
|
||||||
|
trt_engine_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), '..', '..', 'trt_engines', 'video_backbone.engine')
|
||||||
|
if os.path.exists(trt_engine_path):
|
||||||
|
model.model.diffusion_model.load_trt_backbone(trt_engine_path)
|
||||||
|
|
||||||
# Run over data
|
# Run over data
|
||||||
assert (args.height % 16 == 0) and (
|
assert (args.height % 16 == 0) and (
|
||||||
args.width % 16
|
args.width % 16
|
||||||
@@ -649,7 +635,7 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
|||||||
sample_save_dir = f'{video_save_dir}/wm/{fs}'
|
sample_save_dir = f'{video_save_dir}/wm/{fs}'
|
||||||
os.makedirs(sample_save_dir, exist_ok=True)
|
os.makedirs(sample_save_dir, exist_ok=True)
|
||||||
# For collecting interaction videos
|
# For collecting interaction videos
|
||||||
wm_latent = []
|
wm_video = []
|
||||||
# Initialize observation queues
|
# Initialize observation queues
|
||||||
cond_obs_queues = {
|
cond_obs_queues = {
|
||||||
"observation.images.top":
|
"observation.images.top":
|
||||||
@@ -705,7 +691,7 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
|||||||
|
|
||||||
# Use world-model in policy to generate action
|
# Use world-model in policy to generate action
|
||||||
print(f'>>> Step {itr}: generating actions ...')
|
print(f'>>> Step {itr}: generating actions ...')
|
||||||
pred_videos_0, pred_actions, _, _ = image_guided_synthesis_sim_mode(
|
pred_videos_0, pred_actions, _ = image_guided_synthesis_sim_mode(
|
||||||
model,
|
model,
|
||||||
sample['instruction'],
|
sample['instruction'],
|
||||||
observation,
|
observation,
|
||||||
@@ -747,7 +733,7 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
|||||||
|
|
||||||
# Interaction with the world-model
|
# Interaction with the world-model
|
||||||
print(f'>>> Step {itr}: interacting with world model ...')
|
print(f'>>> Step {itr}: interacting with world model ...')
|
||||||
pred_videos_1, _, pred_states, wm_samples = image_guided_synthesis_sim_mode(
|
pred_videos_1, _, pred_states = image_guided_synthesis_sim_mode(
|
||||||
model,
|
model,
|
||||||
"",
|
"",
|
||||||
observation,
|
observation,
|
||||||
@@ -760,16 +746,12 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
|||||||
fs=model_input_fs,
|
fs=model_input_fs,
|
||||||
text_input=False,
|
text_input=False,
|
||||||
timestep_spacing=args.timestep_spacing,
|
timestep_spacing=args.timestep_spacing,
|
||||||
guidance_rescale=args.guidance_rescale,
|
guidance_rescale=args.guidance_rescale)
|
||||||
decode_video=False)
|
|
||||||
|
|
||||||
# Decode only the last frame for CLIP embedding in next iteration
|
|
||||||
last_frame_pixel = model.decode_first_stage(wm_samples[:, :, -1:, :, :])
|
|
||||||
|
|
||||||
for idx in range(args.exe_steps):
|
for idx in range(args.exe_steps):
|
||||||
observation = {
|
observation = {
|
||||||
'observation.images.top':
|
'observation.images.top':
|
||||||
last_frame_pixel[0, :, 0:1].permute(1, 0, 2, 3),
|
pred_videos_1[0][:, idx:idx + 1].permute(1, 0, 2, 3),
|
||||||
'observation.state':
|
'observation.state':
|
||||||
torch.zeros_like(pred_states[0][idx:idx + 1]) if
|
torch.zeros_like(pred_states[0][idx:idx + 1]) if
|
||||||
args.zero_pred_state else pred_states[0][idx:idx + 1],
|
args.zero_pred_state else pred_states[0][idx:idx + 1],
|
||||||
@@ -787,14 +769,30 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
|
|||||||
pred_videos_0,
|
pred_videos_0,
|
||||||
sample_tag,
|
sample_tag,
|
||||||
fps=args.save_fps)
|
fps=args.save_fps)
|
||||||
|
# Save videos environment changes via world-model interaction
|
||||||
|
sample_tag = f"{args.dataset}-vid{sample['videoid']}-wd-fs-{fs}/itr-{itr}"
|
||||||
|
log_to_tensorboard_async(writer,
|
||||||
|
pred_videos_1,
|
||||||
|
sample_tag,
|
||||||
|
fps=args.save_fps)
|
||||||
|
|
||||||
|
# Save the imagen videos for decision-making
|
||||||
|
if pred_videos_0 is not None:
|
||||||
|
sample_video_file = f'{video_save_dir}/dm/{fs}/itr-{itr}.mp4'
|
||||||
|
save_results_async(pred_videos_0,
|
||||||
|
sample_video_file,
|
||||||
|
fps=args.save_fps)
|
||||||
|
# Save videos environment changes via world-model interaction
|
||||||
|
sample_video_file = f'{video_save_dir}/wm/{fs}/itr-{itr}.mp4'
|
||||||
|
save_results_async(pred_videos_1,
|
||||||
|
sample_video_file,
|
||||||
|
fps=args.save_fps)
|
||||||
|
|
||||||
print('>' * 24)
|
print('>' * 24)
|
||||||
# Store raw latent for deferred decode
|
# Collect the result of world-model interactions
|
||||||
wm_latent.append(wm_samples[:, :, :args.exe_steps].cpu())
|
wm_video.append(pred_videos_1[:, :, :args.exe_steps].cpu())
|
||||||
|
|
||||||
# Deferred decode: batch decode all stored latents
|
full_video = torch.cat(wm_video, dim=2)
|
||||||
full_latent = torch.cat(wm_latent, dim=2).to(device)
|
|
||||||
full_video = model.decode_first_stage(full_latent).cpu()
|
|
||||||
sample_tag = f"{args.dataset}-vid{sample['videoid']}-wd-fs-{fs}/full"
|
sample_tag = f"{args.dataset}-vid{sample['videoid']}-wd-fs-{fs}/full"
|
||||||
log_to_tensorboard_async(writer,
|
log_to_tensorboard_async(writer,
|
||||||
full_video,
|
full_video,
|
||||||
@@ -922,7 +920,7 @@ def get_parser():
|
|||||||
parser.add_argument(
|
parser.add_argument(
|
||||||
"--fast_policy_no_decode",
|
"--fast_policy_no_decode",
|
||||||
action='store_true',
|
action='store_true',
|
||||||
default=True,
|
default=False,
|
||||||
help="Speed mode: policy pass only predicts actions, skip policy video decode/log/save.")
|
help="Speed mode: policy pass only predicts actions, skip policy video decode/log/save.")
|
||||||
parser.add_argument("--save_fps",
|
parser.add_argument("--save_fps",
|
||||||
type=int,
|
type=int,
|
||||||
|
|||||||
87
scripts/export_trt.py
Normal file
87
scripts/export_trt.py
Normal file
@@ -0,0 +1,87 @@
|
|||||||
|
"""Export video UNet backbone to ONNX, then convert to TensorRT engine.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python scripts/export_trt.py \
|
||||||
|
--ckpt ckpts/unifolm_wma_dual.ckpt.prepared.pt \
|
||||||
|
--config configs/inference/world_model_interaction.yaml \
|
||||||
|
--out_dir trt_engines
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import argparse
|
||||||
|
|
||||||
|
import torch
|
||||||
|
import tensorrt as trt
|
||||||
|
from omegaconf import OmegaConf
|
||||||
|
|
||||||
|
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'src'))
|
||||||
|
from unifolm_wma.utils.utils import instantiate_from_config
|
||||||
|
from unifolm_wma.trt_utils import export_backbone_onnx
|
||||||
|
|
||||||
|
|
||||||
|
def load_model(config_path, ckpt_path):
|
||||||
|
if ckpt_path.endswith('.prepared.pt'):
|
||||||
|
model = torch.load(ckpt_path, map_location='cpu')
|
||||||
|
else:
|
||||||
|
config = OmegaConf.load(config_path)
|
||||||
|
model = instantiate_from_config(config.model)
|
||||||
|
state_dict = torch.load(ckpt_path, map_location='cpu')
|
||||||
|
if 'state_dict' in state_dict:
|
||||||
|
state_dict = state_dict['state_dict']
|
||||||
|
model.load_state_dict(state_dict, strict=False)
|
||||||
|
model.eval().cuda()
|
||||||
|
return model
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
parser.add_argument('--ckpt', required=True)
|
||||||
|
parser.add_argument('--config', default='configs/inference/world_model_interaction.yaml')
|
||||||
|
parser.add_argument('--out_dir', default='trt_engines')
|
||||||
|
parser.add_argument('--context_len', type=int, default=95)
|
||||||
|
parser.add_argument('--fp16', action='store_true', default=True)
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
os.makedirs(args.out_dir, exist_ok=True)
|
||||||
|
onnx_path = os.path.join(args.out_dir, 'video_backbone.onnx')
|
||||||
|
engine_path = os.path.join(args.out_dir, 'video_backbone.engine')
|
||||||
|
|
||||||
|
if os.path.exists(onnx_path):
|
||||||
|
print(f">>> ONNX already exists at {onnx_path}, skipping export.")
|
||||||
|
n_outputs = 10
|
||||||
|
else:
|
||||||
|
print(">>> Loading model ...")
|
||||||
|
model = load_model(args.config, args.ckpt)
|
||||||
|
print(">>> Exporting ONNX ...")
|
||||||
|
with torch.no_grad():
|
||||||
|
n_outputs = export_backbone_onnx(model, onnx_path, context_len=args.context_len)
|
||||||
|
del model
|
||||||
|
torch.cuda.empty_cache()
|
||||||
|
|
||||||
|
print(">>> Converting ONNX -> TensorRT engine ...")
|
||||||
|
logger = trt.Logger(trt.Logger.WARNING)
|
||||||
|
builder = trt.Builder(logger)
|
||||||
|
network = builder.create_network(1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
|
||||||
|
parser = trt.OnnxParser(network, logger)
|
||||||
|
|
||||||
|
if not parser.parse_from_file(os.path.abspath(onnx_path)):
|
||||||
|
for i in range(parser.num_errors):
|
||||||
|
print(f" ONNX parse error: {parser.get_error(i)}")
|
||||||
|
raise RuntimeError("ONNX parsing failed")
|
||||||
|
|
||||||
|
config = builder.create_builder_config()
|
||||||
|
config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, 16 << 30)
|
||||||
|
if args.fp16:
|
||||||
|
config.set_flag(trt.BuilderFlag.FP16)
|
||||||
|
|
||||||
|
engine_bytes = builder.build_serialized_network(network, config)
|
||||||
|
with open(engine_path, 'wb') as f:
|
||||||
|
f.write(engine_bytes)
|
||||||
|
|
||||||
|
print(f"\n>>> Done! Engine saved to {engine_path}")
|
||||||
|
print(f" Outputs: 1 y + {n_outputs - 1} hs_a tensors")
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
main()
|
||||||
@@ -988,7 +988,7 @@ class LatentDiffusion(DDPM):
|
|||||||
|
|
||||||
def instantiate_cond_stage(self, config: OmegaConf) -> None:
|
def instantiate_cond_stage(self, config: OmegaConf) -> None:
|
||||||
"""
|
"""
|
||||||
Build the conditioning stage model. Frozen models are converted to FP16.
|
Build the conditioning stage model.
|
||||||
|
|
||||||
Args:
|
Args:
|
||||||
config: OmegaConf config describing the conditioning model to instantiate.
|
config: OmegaConf config describing the conditioning model to instantiate.
|
||||||
@@ -1000,7 +1000,6 @@ class LatentDiffusion(DDPM):
|
|||||||
self.cond_stage_model.train = disabled_train
|
self.cond_stage_model.train = disabled_train
|
||||||
for param in self.cond_stage_model.parameters():
|
for param in self.cond_stage_model.parameters():
|
||||||
param.requires_grad = False
|
param.requires_grad = False
|
||||||
self.cond_stage_model.half()
|
|
||||||
else:
|
else:
|
||||||
model = instantiate_from_config(config)
|
model = instantiate_from_config(config)
|
||||||
self.cond_stage_model = model
|
self.cond_stage_model = model
|
||||||
@@ -1015,18 +1014,17 @@ class LatentDiffusion(DDPM):
|
|||||||
Returns:
|
Returns:
|
||||||
Conditioning embedding as a tensor (shape depends on cond model).
|
Conditioning embedding as a tensor (shape depends on cond model).
|
||||||
"""
|
"""
|
||||||
with torch.cuda.amp.autocast(dtype=torch.float16):
|
if self.cond_stage_forward is None:
|
||||||
if self.cond_stage_forward is None:
|
if hasattr(self.cond_stage_model, 'encode') and callable(
|
||||||
if hasattr(self.cond_stage_model, 'encode') and callable(
|
self.cond_stage_model.encode):
|
||||||
self.cond_stage_model.encode):
|
c = self.cond_stage_model.encode(c)
|
||||||
c = self.cond_stage_model.encode(c)
|
if isinstance(c, DiagonalGaussianDistribution):
|
||||||
if isinstance(c, DiagonalGaussianDistribution):
|
c = c.mode()
|
||||||
c = c.mode()
|
|
||||||
else:
|
|
||||||
c = self.cond_stage_model(c)
|
|
||||||
else:
|
else:
|
||||||
assert hasattr(self.cond_stage_model, self.cond_stage_forward)
|
c = self.cond_stage_model(c)
|
||||||
c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
|
else:
|
||||||
|
assert hasattr(self.cond_stage_model, self.cond_stage_forward)
|
||||||
|
c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
|
||||||
return c
|
return c
|
||||||
|
|
||||||
def get_first_stage_encoding(
|
def get_first_stage_encoding(
|
||||||
@@ -1959,7 +1957,6 @@ class LatentVisualDiffusion(LatentDiffusion):
|
|||||||
self.image_proj_model.train = disabled_train
|
self.image_proj_model.train = disabled_train
|
||||||
for param in self.image_proj_model.parameters():
|
for param in self.image_proj_model.parameters():
|
||||||
param.requires_grad = False
|
param.requires_grad = False
|
||||||
self.image_proj_model.half()
|
|
||||||
|
|
||||||
def _init_embedder(self, config: OmegaConf, freeze: bool = True) -> None:
|
def _init_embedder(self, config: OmegaConf, freeze: bool = True) -> None:
|
||||||
"""
|
"""
|
||||||
@@ -1975,7 +1972,6 @@ class LatentVisualDiffusion(LatentDiffusion):
|
|||||||
self.embedder.train = disabled_train
|
self.embedder.train = disabled_train
|
||||||
for param in self.embedder.parameters():
|
for param in self.embedder.parameters():
|
||||||
param.requires_grad = False
|
param.requires_grad = False
|
||||||
self.embedder.half()
|
|
||||||
|
|
||||||
def init_normalizers(self, normalize_config: OmegaConf,
|
def init_normalizers(self, normalize_config: OmegaConf,
|
||||||
dataset_stats: Mapping[str, Any]) -> None:
|
dataset_stats: Mapping[str, Any]) -> None:
|
||||||
@@ -2179,9 +2175,8 @@ class LatentVisualDiffusion(LatentDiffusion):
|
|||||||
(random_num < 3 * self.uncond_prob).float(), "n -> n 1 1 1")
|
(random_num < 3 * self.uncond_prob).float(), "n -> n 1 1 1")
|
||||||
|
|
||||||
cond_img = input_mask * img
|
cond_img = input_mask * img
|
||||||
with torch.cuda.amp.autocast(dtype=torch.float16):
|
cond_img_emb = self.embedder(cond_img)
|
||||||
cond_img_emb = self.embedder(cond_img)
|
cond_img_emb = self.image_proj_model(cond_img_emb)
|
||||||
cond_img_emb = self.image_proj_model(cond_img_emb)
|
|
||||||
|
|
||||||
if self.model.conditioning_key == 'hybrid':
|
if self.model.conditioning_key == 'hybrid':
|
||||||
if self.interp_mode:
|
if self.interp_mode:
|
||||||
@@ -2196,12 +2191,11 @@ class LatentVisualDiffusion(LatentDiffusion):
|
|||||||
repeat=z.shape[2])
|
repeat=z.shape[2])
|
||||||
cond["c_concat"] = [img_cat_cond]
|
cond["c_concat"] = [img_cat_cond]
|
||||||
|
|
||||||
with torch.cuda.amp.autocast(dtype=torch.float16):
|
cond_action = self.action_projector(action)
|
||||||
cond_action = self.action_projector(action)
|
cond_action_emb = self.agent_action_pos_emb + cond_action
|
||||||
cond_action_emb = self.agent_action_pos_emb + cond_action
|
# Get conditioning states
|
||||||
# Get conditioning states
|
cond_state = self.state_projector(obs_state)
|
||||||
cond_state = self.state_projector(obs_state)
|
cond_state_emb = self.agent_state_pos_emb + cond_state
|
||||||
cond_state_emb = self.agent_state_pos_emb + cond_state
|
|
||||||
|
|
||||||
if self.decision_making_only:
|
if self.decision_making_only:
|
||||||
is_sim_mode = False
|
is_sim_mode = False
|
||||||
@@ -2463,17 +2457,7 @@ class DiffusionWrapper(pl.LightningModule):
|
|||||||
Returns:
|
Returns:
|
||||||
Output from the inner diffusion model (tensor or tuple, depending on the model).
|
Output from the inner diffusion model (tensor or tuple, depending on the model).
|
||||||
"""
|
"""
|
||||||
with torch.cuda.amp.autocast(dtype=torch.float16):
|
|
||||||
return self._forward_impl(x, x_action, x_state, t,
|
|
||||||
c_concat, c_crossattn, c_crossattn_action,
|
|
||||||
c_adm, s, mask, **kwargs)
|
|
||||||
|
|
||||||
def _forward_impl(
|
|
||||||
self,
|
|
||||||
x, x_action, x_state, t,
|
|
||||||
c_concat=None, c_crossattn=None, c_crossattn_action=None,
|
|
||||||
c_adm=None, s=None, mask=None, **kwargs,
|
|
||||||
):
|
|
||||||
if self.conditioning_key is None:
|
if self.conditioning_key is None:
|
||||||
out = self.diffusion_model(x, t)
|
out = self.diffusion_model(x, t)
|
||||||
elif self.conditioning_key == 'concat':
|
elif self.conditioning_key == 'concat':
|
||||||
|
|||||||
@@ -688,6 +688,7 @@ class WMAModel(nn.Module):
|
|||||||
# Context precomputation cache
|
# Context precomputation cache
|
||||||
self._ctx_cache_enabled = False
|
self._ctx_cache_enabled = False
|
||||||
self._ctx_cache = {}
|
self._ctx_cache = {}
|
||||||
|
self._trt_backbone = None # TRT engine for video UNet backbone
|
||||||
# Reusable CUDA stream for parallel state_unet / action_unet
|
# Reusable CUDA stream for parallel state_unet / action_unet
|
||||||
self._state_stream = torch.cuda.Stream()
|
self._state_stream = torch.cuda.Stream()
|
||||||
|
|
||||||
@@ -700,6 +701,12 @@ class WMAModel(nn.Module):
|
|||||||
self.__dict__.update(state)
|
self.__dict__.update(state)
|
||||||
self._state_stream = torch.cuda.Stream()
|
self._state_stream = torch.cuda.Stream()
|
||||||
|
|
||||||
|
def load_trt_backbone(self, engine_path, n_hs_a=9):
|
||||||
|
"""Load a TensorRT engine for the video UNet backbone."""
|
||||||
|
from unifolm_wma.trt_utils import TRTBackbone
|
||||||
|
self._trt_backbone = TRTBackbone(engine_path, n_hs_a=n_hs_a)
|
||||||
|
print(f">>> TRT backbone loaded from {engine_path}")
|
||||||
|
|
||||||
def forward(self,
|
def forward(self,
|
||||||
x: Tensor,
|
x: Tensor,
|
||||||
x_action: Tensor,
|
x_action: Tensor,
|
||||||
@@ -812,44 +819,50 @@ class WMAModel(nn.Module):
|
|||||||
fs_embed = fs_embed.repeat_interleave(repeats=t, dim=0)
|
fs_embed = fs_embed.repeat_interleave(repeats=t, dim=0)
|
||||||
emb = emb + fs_embed
|
emb = emb + fs_embed
|
||||||
|
|
||||||
h = x.type(self.dtype)
|
if self._trt_backbone is not None:
|
||||||
adapter_idx = 0
|
# TRT path: run backbone via TensorRT engine
|
||||||
hs = []
|
h_in = x.type(self.dtype).contiguous()
|
||||||
hs_a = []
|
y, hs_a = self._trt_backbone(h_in, emb.contiguous(), context.contiguous())
|
||||||
for id, module in enumerate(self.input_blocks):
|
else:
|
||||||
h = module(h, emb, context=context, batch_size=b)
|
# PyTorch path: original backbone
|
||||||
if id == 0 and self.addition_attention:
|
h = x.type(self.dtype)
|
||||||
h = self.init_attn(h, emb, context=context, batch_size=b)
|
adapter_idx = 0
|
||||||
# plug-in adapter features
|
hs = []
|
||||||
if ((id + 1) % 3 == 0) and features_adapter is not None:
|
hs_a = []
|
||||||
h = h + features_adapter[adapter_idx]
|
for id, module in enumerate(self.input_blocks):
|
||||||
adapter_idx += 1
|
h = module(h, emb, context=context, batch_size=b)
|
||||||
if id != 0:
|
if id == 0 and self.addition_attention:
|
||||||
if isinstance(module[0], Downsample):
|
h = self.init_attn(h, emb, context=context, batch_size=b)
|
||||||
|
# plug-in adapter features
|
||||||
|
if ((id + 1) % 3 == 0) and features_adapter is not None:
|
||||||
|
h = h + features_adapter[adapter_idx]
|
||||||
|
adapter_idx += 1
|
||||||
|
if id != 0:
|
||||||
|
if isinstance(module[0], Downsample):
|
||||||
|
hs_a.append(
|
||||||
|
rearrange(hs[-1], '(b t) c h w -> b t c h w', t=t))
|
||||||
|
hs.append(h)
|
||||||
|
hs_a.append(rearrange(h, '(b t) c h w -> b t c h w', t=t))
|
||||||
|
|
||||||
|
if features_adapter is not None:
|
||||||
|
assert len(
|
||||||
|
features_adapter) == adapter_idx, 'Wrong features_adapter'
|
||||||
|
h = self.middle_block(h, emb, context=context, batch_size=b)
|
||||||
|
hs_a.append(rearrange(h, '(b t) c h w -> b t c h w', t=t))
|
||||||
|
|
||||||
|
hs_out = []
|
||||||
|
for module in self.output_blocks:
|
||||||
|
h = torch.cat([h, hs.pop()], dim=1)
|
||||||
|
h = module(h, emb, context=context, batch_size=b)
|
||||||
|
if isinstance(module[-1], Upsample):
|
||||||
hs_a.append(
|
hs_a.append(
|
||||||
rearrange(hs[-1], '(b t) c h w -> b t c h w', t=t))
|
rearrange(hs_out[-1], '(b t) c h w -> b t c h w', t=t))
|
||||||
hs.append(h)
|
hs_out.append(h)
|
||||||
hs_a.append(rearrange(h, '(b t) c h w -> b t c h w', t=t))
|
h = h.type(x.dtype)
|
||||||
|
hs_a.append(rearrange(hs_out[-1], '(b t) c h w -> b t c h w', t=t))
|
||||||
|
|
||||||
if features_adapter is not None:
|
y = self.out(h)
|
||||||
assert len(
|
y = rearrange(y, '(b t) c h w -> b c t h w', b=b)
|
||||||
features_adapter) == adapter_idx, 'Wrong features_adapter'
|
|
||||||
h = self.middle_block(h, emb, context=context, batch_size=b)
|
|
||||||
hs_a.append(rearrange(h, '(b t) c h w -> b t c h w', t=t))
|
|
||||||
|
|
||||||
hs_out = []
|
|
||||||
for module in self.output_blocks:
|
|
||||||
h = torch.cat([h, hs.pop()], dim=1)
|
|
||||||
h = module(h, emb, context=context, batch_size=b)
|
|
||||||
if isinstance(module[-1], Upsample):
|
|
||||||
hs_a.append(
|
|
||||||
rearrange(hs_out[-1], '(b t) c h w -> b t c h w', t=t))
|
|
||||||
hs_out.append(h)
|
|
||||||
h = h.type(x.dtype)
|
|
||||||
hs_a.append(rearrange(hs_out[-1], '(b t) c h w -> b t c h w', t=t))
|
|
||||||
|
|
||||||
y = self.out(h)
|
|
||||||
y = rearrange(y, '(b t) c h w -> b c t h w', b=b)
|
|
||||||
|
|
||||||
if not self.base_model_gen_only:
|
if not self.base_model_gen_only:
|
||||||
ba, _, _ = x_action.shape
|
ba, _, _ = x_action.shape
|
||||||
|
|||||||
151
src/unifolm_wma/trt_utils.py
Normal file
151
src/unifolm_wma/trt_utils.py
Normal file
@@ -0,0 +1,151 @@
|
|||||||
|
"""TensorRT acceleration utilities for the video UNet backbone."""
|
||||||
|
|
||||||
|
import torch
|
||||||
|
import torch.nn as nn
|
||||||
|
from einops import rearrange
|
||||||
|
from unifolm_wma.modules.networks.wma_model import Downsample, Upsample
|
||||||
|
|
||||||
|
|
||||||
|
class VideoBackboneForExport(nn.Module):
|
||||||
|
"""Wrapper that isolates the video UNet backbone for ONNX export.
|
||||||
|
|
||||||
|
Takes already-preprocessed inputs (after context/time embedding prep)
|
||||||
|
and returns y + hs_a as a flat tuple.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(self, wma_model):
|
||||||
|
super().__init__()
|
||||||
|
self.input_blocks = wma_model.input_blocks
|
||||||
|
self.middle_block = wma_model.middle_block
|
||||||
|
self.output_blocks = wma_model.output_blocks
|
||||||
|
self.out = wma_model.out
|
||||||
|
self.addition_attention = wma_model.addition_attention
|
||||||
|
if self.addition_attention:
|
||||||
|
self.init_attn = wma_model.init_attn
|
||||||
|
self.dtype = wma_model.dtype
|
||||||
|
|
||||||
|
def forward(self, h, emb, context):
|
||||||
|
t = 16
|
||||||
|
b = 1
|
||||||
|
|
||||||
|
hs = []
|
||||||
|
hs_a = []
|
||||||
|
h = h.type(self.dtype)
|
||||||
|
for id, module in enumerate(self.input_blocks):
|
||||||
|
h = module(h, emb, context=context, batch_size=b)
|
||||||
|
if id == 0 and self.addition_attention:
|
||||||
|
h = self.init_attn(h, emb, context=context, batch_size=b)
|
||||||
|
if id != 0:
|
||||||
|
if isinstance(module[0], Downsample):
|
||||||
|
hs_a.append(rearrange(hs[-1], '(b t) c h w -> b t c h w', t=t))
|
||||||
|
hs.append(h)
|
||||||
|
hs_a.append(rearrange(h, '(b t) c h w -> b t c h w', t=t))
|
||||||
|
|
||||||
|
h = self.middle_block(h, emb, context=context, batch_size=b)
|
||||||
|
hs_a.append(rearrange(h, '(b t) c h w -> b t c h w', t=t))
|
||||||
|
|
||||||
|
hs_out = []
|
||||||
|
for module in self.output_blocks:
|
||||||
|
h = torch.cat([h, hs.pop()], dim=1)
|
||||||
|
h = module(h, emb, context=context, batch_size=b)
|
||||||
|
if isinstance(module[-1], Upsample):
|
||||||
|
hs_a.append(rearrange(hs_out[-1], '(b t) c h w -> b t c h w', t=t))
|
||||||
|
hs_out.append(h)
|
||||||
|
hs_a.append(rearrange(hs_out[-1], '(b t) c h w -> b t c h w', t=t))
|
||||||
|
|
||||||
|
y = self.out(h.type(h.dtype))
|
||||||
|
y = rearrange(y, '(b t) c h w -> b c t h w', b=b)
|
||||||
|
return (y, *hs_a)
|
||||||
|
|
||||||
|
|
||||||
|
def export_backbone_onnx(model, save_path, context_len=95):
|
||||||
|
wma = model.model.diffusion_model
|
||||||
|
wrapper = VideoBackboneForExport(wma)
|
||||||
|
wrapper.eval().cuda()
|
||||||
|
|
||||||
|
for m in wrapper.modules():
|
||||||
|
if hasattr(m, 'checkpoint'):
|
||||||
|
m.checkpoint = False
|
||||||
|
if hasattr(m, 'use_checkpoint'):
|
||||||
|
m.use_checkpoint = False
|
||||||
|
|
||||||
|
import xformers.ops
|
||||||
|
_orig_mea = xformers.ops.memory_efficient_attention
|
||||||
|
def _sdpa_replacement(q, k, v, attn_bias=None, op=None, **kw):
|
||||||
|
return torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=attn_bias)
|
||||||
|
xformers.ops.memory_efficient_attention = _sdpa_replacement
|
||||||
|
|
||||||
|
BT = 16
|
||||||
|
emb_dim = wma.model_channels * 4
|
||||||
|
ctx_dim = 1024
|
||||||
|
in_ch = wma.in_channels
|
||||||
|
|
||||||
|
dummy_h = torch.randn(BT, in_ch, 40, 64, device='cuda', dtype=torch.float32)
|
||||||
|
dummy_emb = torch.randn(BT, emb_dim, device='cuda', dtype=torch.float32)
|
||||||
|
dummy_ctx = torch.randn(BT, context_len, ctx_dim, device='cuda', dtype=torch.float32)
|
||||||
|
|
||||||
|
with torch.no_grad():
|
||||||
|
outputs = wrapper(dummy_h, dummy_emb, dummy_ctx)
|
||||||
|
n_outputs = len(outputs)
|
||||||
|
print(f">>> Backbone has {n_outputs} outputs (1 y + {n_outputs-1} hs_a)")
|
||||||
|
for i, o in enumerate(outputs):
|
||||||
|
print(f" output[{i}]: {o.shape} {o.dtype}")
|
||||||
|
|
||||||
|
output_names = ['y'] + [f'hs_a_{i}' for i in range(n_outputs - 1)]
|
||||||
|
|
||||||
|
torch.onnx.export(
|
||||||
|
wrapper,
|
||||||
|
(dummy_h, dummy_emb, dummy_ctx),
|
||||||
|
save_path,
|
||||||
|
input_names=['h', 'emb', 'context'],
|
||||||
|
output_names=output_names,
|
||||||
|
opset_version=17,
|
||||||
|
do_constant_folding=True,
|
||||||
|
)
|
||||||
|
print(f">>> ONNX exported to {save_path}")
|
||||||
|
xformers.ops.memory_efficient_attention = _orig_mea
|
||||||
|
return n_outputs
|
||||||
|
|
||||||
|
|
||||||
|
class TRTBackbone:
|
||||||
|
"""TensorRT runtime wrapper for the video UNet backbone."""
|
||||||
|
|
||||||
|
def __init__(self, engine_path, n_hs_a=9):
|
||||||
|
import tensorrt as trt
|
||||||
|
|
||||||
|
self.logger = trt.Logger(trt.Logger.WARNING)
|
||||||
|
with open(engine_path, 'rb') as f:
|
||||||
|
runtime = trt.Runtime(self.logger)
|
||||||
|
self.engine = runtime.deserialize_cuda_engine(f.read())
|
||||||
|
self.context = self.engine.create_execution_context()
|
||||||
|
self.n_hs_a = n_hs_a
|
||||||
|
|
||||||
|
import numpy as np
|
||||||
|
self.output_buffers = {}
|
||||||
|
for i in range(self.engine.num_io_tensors):
|
||||||
|
name = self.engine.get_tensor_name(i)
|
||||||
|
if self.engine.get_tensor_mode(name) == trt.TensorIOMode.OUTPUT:
|
||||||
|
shape = self.engine.get_tensor_shape(name)
|
||||||
|
np_dtype = trt.nptype(self.engine.get_tensor_dtype(name))
|
||||||
|
buf = torch.empty(list(shape), dtype=torch.from_numpy(np.empty(0, dtype=np_dtype)).dtype, device='cuda')
|
||||||
|
self.output_buffers[name] = buf
|
||||||
|
print(f" TRT output '{name}': {list(shape)} {buf.dtype}")
|
||||||
|
|
||||||
|
def __call__(self, h, emb, context):
|
||||||
|
import tensorrt as trt
|
||||||
|
for name, tensor in [('h', h), ('emb', emb), ('context', context)]:
|
||||||
|
expected_dtype = trt.nptype(self.engine.get_tensor_dtype(name))
|
||||||
|
torch_expected = torch.from_numpy(__import__('numpy').empty(0, dtype=expected_dtype)).dtype
|
||||||
|
if tensor.dtype != torch_expected:
|
||||||
|
tensor = tensor.to(torch_expected)
|
||||||
|
self.context.set_tensor_address(name, tensor.contiguous().data_ptr())
|
||||||
|
|
||||||
|
for name, buf in self.output_buffers.items():
|
||||||
|
self.context.set_tensor_address(name, buf.data_ptr())
|
||||||
|
|
||||||
|
self.context.execute_async_v3(torch.cuda.current_stream().cuda_stream)
|
||||||
|
torch.cuda.synchronize()
|
||||||
|
|
||||||
|
y = self.output_buffers['y']
|
||||||
|
hs_a = [self.output_buffers[f'hs_a_{i}'] for i in range(self.n_hs_a)]
|
||||||
|
return y, hs_a
|
||||||
@@ -1,16 +1,13 @@
|
|||||||
2026-02-11 19:14:09.599811: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
2026-02-18 19:01:56.891895: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
2026-02-11 19:14:09.649058: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
2026-02-18 19:01:56.940243: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
2026-02-11 19:14:09.649103: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
2026-02-18 19:01:56.940285: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
2026-02-11 19:14:09.650392: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
2026-02-18 19:01:56.941395: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
2026-02-11 19:14:09.657857: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
2026-02-18 19:01:56.948327: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
2026-02-11 19:14:10.584900: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
2026-02-18 19:01:57.870809: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
Global seed set to 123
|
Global seed set to 123
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
>>> Prepared model loaded.
|
>>> Prepared model loaded.
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
INFO:root:***** Configing Data *****
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
@@ -29,16 +26,124 @@ INFO:root:***** Configing Data *****
|
|||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
>>> Dataset is successfully loaded ...
|
>>> Dataset is successfully loaded ...
|
||||||
✓ KV fused: 66 attention layers
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
>>> Generate 16 frames under each generation ...
|
>>> Generate 16 frames under each generation ...
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-19:02:10] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
9%|▉ | 1/11 [00:17<02:51, 17.15s/it]>>> Step 0: generating actions ...
|
9%|▉ | 1/11 [00:17<02:51, 17.15s/it]>>> Step 0: generating actions ...
|
||||||
>>> Step 0: interacting with world model ...
|
>>> Step 0: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 1: generating actions ...
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
|
||||||
18%|█▊ | 2/11 [00:33<02:31, 16.87s/it]
|
18%|█▊ | 2/11 [00:33<02:31, 16.87s/it]
|
||||||
@@ -68,56 +173,7 @@ DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
>>> Step 6: generating actions ...
|
>>> Step 6: generating actions ...
|
||||||
>>> Step 6: interacting with world model ...
|
>>> Step 6: interacting with world model ...
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
>>> Step 7: generating actions ...
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
>>> Step 7: interacting with world model ...
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_g1_pack_camera/case1/unitree_g1_pack_camera_case1.mp4",
|
"gt_video": "unitree_g1_pack_camera/case1/unitree_g1_pack_camera_case1.mp4",
|
||||||
"pred_video": "unitree_g1_pack_camera/case1/output/inference/0_full_fs6.mp4",
|
"pred_video": "unitree_g1_pack_camera/case1/output/inference/0_full_fs6.mp4",
|
||||||
"psnr": 32.340256576190384
|
"psnr": 35.615362167470806
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_g1_pack_camera"
|
|||||||
--n_iter 11 \
|
--n_iter 11 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,16 +1,13 @@
|
|||||||
2026-02-11 17:41:30.163933: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
2026-02-18 19:05:45.956647: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
2026-02-11 17:41:30.213409: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
2026-02-18 19:05:46.004149: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
2026-02-11 17:41:30.213453: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
2026-02-18 19:05:46.004193: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
2026-02-11 17:41:30.214760: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
2026-02-18 19:05:46.005265: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
2026-02-11 17:41:30.222233: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
2026-02-18 19:05:46.012074: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
2026-02-11 17:41:31.146811: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
2026-02-18 19:05:46.932966: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
Global seed set to 123
|
Global seed set to 123
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
>>> Prepared model loaded.
|
>>> Prepared model loaded.
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
INFO:root:***** Configing Data *****
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
@@ -29,16 +26,124 @@ INFO:root:***** Configing Data *****
|
|||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
>>> Dataset is successfully loaded ...
|
>>> Dataset is successfully loaded ...
|
||||||
✓ KV fused: 66 attention layers
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
>>> Generate 16 frames under each generation ...
|
>>> Generate 16 frames under each generation ...
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-19:05:59] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
9%|▉ | 1/11 [00:16<02:47, 16.71s/it]>>> Step 0: generating actions ...
|
9%|▉ | 1/11 [00:16<02:47, 16.71s/it]>>> Step 0: generating actions ...
|
||||||
>>> Step 0: interacting with world model ...
|
>>> Step 0: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 1: generating actions ...
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
|
||||||
18%|█▊ | 2/11 [00:33<02:30, 16.75s/it]
|
18%|█▊ | 2/11 [00:33<02:30, 16.75s/it]
|
||||||
@@ -68,56 +173,7 @@ DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
>>> Step 6: generating actions ...
|
>>> Step 6: generating actions ...
|
||||||
>>> Step 6: interacting with world model ...
|
>>> Step 6: interacting with world model ...
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
>>> Step 7: generating actions ...
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
>>> Step 7: interacting with world model ...
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_g1_pack_camera/case2/unitree_g1_pack_camera_case2.mp4",
|
"gt_video": "unitree_g1_pack_camera/case2/unitree_g1_pack_camera_case2.mp4",
|
||||||
"pred_video": "unitree_g1_pack_camera/case2/output/inference/50_full_fs6.mp4",
|
"pred_video": "unitree_g1_pack_camera/case2/output/inference/50_full_fs6.mp4",
|
||||||
"psnr": 37.49178506869336
|
"psnr": 34.61979248212279
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_g1_pack_camera"
|
|||||||
--n_iter 11 \
|
--n_iter 11 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,16 +1,13 @@
|
|||||||
2026-02-11 17:46:20.925463: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
2026-02-18 19:09:35.113634: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
2026-02-11 17:46:20.976293: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
2026-02-18 19:09:35.161428: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
2026-02-11 17:46:20.976338: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
2026-02-18 19:09:35.161474: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
2026-02-11 17:46:20.977650: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
2026-02-18 19:09:35.162551: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
2026-02-11 17:46:20.985133: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
2026-02-18 19:09:35.169325: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
2026-02-11 17:46:21.909964: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
2026-02-18 19:09:36.089250: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
Global seed set to 123
|
Global seed set to 123
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
>>> Prepared model loaded.
|
>>> Prepared model loaded.
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
INFO:root:***** Configing Data *****
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
@@ -29,95 +26,121 @@ INFO:root:***** Configing Data *****
|
|||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
>>> Dataset is successfully loaded ...
|
>>> Dataset is successfully loaded ...
|
||||||
✓ KV fused: 66 attention layers
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
>>> Generate 16 frames under each generation ...
|
>>> Generate 16 frames under each generation ...
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-19:09:49] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
9%|▉ | 1/11 [00:16<02:45, 16.53s/it]>>> Step 0: generating actions ...
|
9%|▉ | 1/11 [00:16<02:45, 16.53s/it]>>> Step 0: generating actions ...
|
||||||
>>> Step 0: interacting with world model ...
|
>>> Step 0: interacting with world model ...
|
||||||
36%|███▋ | 4/11 [01:32<02:40, 22.94s/it]
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
45%|████▌ | 5/11 [01:54<02:17, 22.90s/it]
|
|
||||||
55%|█████▍ | 6/11 [02:17<01:54, 22.87s/it]
|
|
||||||
64%|██████▎ | 7/11 [02:40<01:31, 22.85s/it]
|
|
||||||
73%|███████▎ | 8/11 [03:03<01:08, 22.83s/it]
|
|
||||||
82%|████████▏ | 9/11 [03:26<00:45, 22.81s/it]
|
|
||||||
91%|█████████ | 10/11 [03:48<00:22, 22.78s/it]
|
|
||||||
100%|██████████| 11/11 [04:11<00:00, 22.76s/it]
|
|
||||||
100%|██████████| 11/11 [04:11<00:00, 22.86s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>> Step 1: generating actions ...
|
>>> Step 1: generating actions ...
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
DEBUG:PIL.Image:Importing WebPImagePlugin
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
DEBUG:PIL.Image:Importing WmfImagePlugin
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XbmImagePlugin
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XpmImagePlugin
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_g1_pack_camera/case3/unitree_g1_pack_camera_case3.mp4",
|
"gt_video": "unitree_g1_pack_camera/case3/unitree_g1_pack_camera_case3.mp4",
|
||||||
"pred_video": "unitree_g1_pack_camera/case3/output/inference/100_full_fs6.mp4",
|
"pred_video": "unitree_g1_pack_camera/case3/output/inference/100_full_fs6.mp4",
|
||||||
"psnr": 29.88155122131729
|
"psnr": 37.034952654534486
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_g1_pack_camera"
|
|||||||
--n_iter 11 \
|
--n_iter 11 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,123 +0,0 @@
|
|||||||
2026-02-11 17:51:11.566934: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 17:51:11.616260: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 17:51:11.616305: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 17:51:11.617626: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 17:51:11.625103: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 17:51:12.538539: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
|
||||||
9%|▉ | 1/11 [00:23<03:53, 23.39s/it]
|
|
||||||
18%|█▊ | 2/11 [00:46<03:26, 22.96s/it]
|
|
||||||
27%|██▋ | 3/11 [01:08<03:03, 22.89s/it]
|
|
||||||
36%|███▋ | 4/11 [01:31<02:40, 22.86s/it]
|
|
||||||
45%|████▌ | 5/11 [01:54<02:16, 22.82s/it]
|
|
||||||
55%|█████▍ | 6/11 [02:17<01:54, 22.80s/it]
|
|
||||||
64%|██████▎ | 7/11 [02:39<01:31, 22.77s/it]
|
|
||||||
73%|███████▎ | 8/11 [03:02<01:08, 22.75s/it]
|
|
||||||
82%|████████▏ | 9/11 [03:25<00:45, 22.73s/it]
|
|
||||||
91%|█████████ | 10/11 [03:47<00:22, 22.72s/it]
|
|
||||||
100%|██████████| 11/11 [04:10<00:00, 22.73s/it]
|
|
||||||
100%|██████████| 11/11 [04:10<00:00, 22.79s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_g1_pack_camera/case4/unitree_g1_pack_camera_case4.mp4",
|
"gt_video": "unitree_g1_pack_camera/case4/unitree_g1_pack_camera_case4.mp4",
|
||||||
"pred_video": "unitree_g1_pack_camera/case4/output/inference/200_full_fs6.mp4",
|
"pred_video": "unitree_g1_pack_camera/case4/output/inference/200_full_fs6.mp4",
|
||||||
"psnr": 35.62512454155058
|
"psnr": 31.43390896360405
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_g1_pack_camera"
|
|||||||
--n_iter 11 \
|
--n_iter 11 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,16 +1,24 @@
|
|||||||
2026-02-11 17:56:01.170137: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
2026-02-10 15:38:28.973314: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
2026-02-11 17:56:01.219541: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
2026-02-10 15:38:29.023024: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
2026-02-11 17:56:01.219584: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
2026-02-10 15:38:29.023070: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
2026-02-11 17:56:01.220897: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
2026-02-10 15:38:29.024393: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
2026-02-11 17:56:01.228350: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
2026-02-10 15:38:29.031901: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
2026-02-11 17:56:02.145344: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
2026-02-10 15:38:29.955454: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
Global seed set to 123
|
Global seed set to 123
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode
|
||||||
>>> Prepared model loaded.
|
INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
AE working on z of shape (1, 4, 32, 32) = 4096 dimensions.
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
INFO:root:Loaded ViT-H-14 model config.
|
||||||
|
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): hf-mirror.com:443
|
||||||
|
DEBUG:urllib3.connectionpool:https://hf-mirror.com:443 "HEAD /laion/CLIP-ViT-H-14-laion2B-s32B-b79K/resolve/main/open_clip_pytorch_model.bin HTTP/1.1" 302 0
|
||||||
|
INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k).
|
||||||
|
INFO:root:Loaded ViT-H-14 model config.
|
||||||
|
DEBUG:urllib3.connectionpool:https://hf-mirror.com:443 "HEAD /laion/CLIP-ViT-H-14-laion2B-s32B-b79K/resolve/main/open_clip_pytorch_model.bin HTTP/1.1" 302 0
|
||||||
|
INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k).
|
||||||
|
>>> model checkpoint loaded.
|
||||||
|
>>> Load pre-trained model ...
|
||||||
INFO:root:***** Configing Data *****
|
INFO:root:***** Configing Data *****
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
@@ -28,37 +36,13 @@ INFO:root:***** Configing Data *****
|
|||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
>>> unitree_g1_pack_camera: data stats loaded.
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
>>> Dataset is successfully loaded ...
|
>>> Dataset is successfully loaded ...
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
>>> Generate 16 frames under each generation ...
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
0%| | 0/8 [00:00<?, ?it/s]
|
|
||||||
0%| | 0/8 [00:00<?, ?it/s]>>> Step 0: generating actions ...
|
0%| | 0/8 [00:00<?, ?it/s]>>> Step 0: generating actions ...
|
||||||
25%|██▌ | 2/8 [00:46<02:17, 22.96s/it]
|
|
||||||
38%|███▊ | 3/8 [01:08<01:54, 22.88s/it]
|
|
||||||
50%|█████ | 4/8 [01:31<01:31, 22.82s/it]
|
|
||||||
62%|██████▎ | 5/8 [01:54<01:08, 22.78s/it]
|
|
||||||
75%|███████▌ | 6/8 [02:16<00:45, 22.76s/it]
|
|
||||||
88%|████████▊ | 7/8 [02:39<00:22, 22.73s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.72s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.79s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
>>> Step 0: interacting with world model ...
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
@@ -108,7 +92,30 @@ DEBUG:PIL.Image:Importing WmfImagePlugin
|
|||||||
DEBUG:PIL.Image:Importing WmfImagePlugin
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XbmImagePlugin
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XpmImagePlugin
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
|
||||||
|
12%|█▎ | 1/8 [01:14<08:41, 74.51s/it]
|
||||||
|
25%|██▌ | 2/8 [02:29<07:28, 74.79s/it]
|
||||||
|
38%|███▊ | 3/8 [03:44<06:14, 74.81s/it]
|
||||||
|
50%|█████ | 4/8 [04:59<04:59, 74.78s/it]
|
||||||
|
62%|██████▎ | 5/8 [06:13<03:44, 74.73s/it]
|
||||||
|
75%|███████▌ | 6/8 [07:28<02:29, 74.66s/it]
|
||||||
|
88%|████████▊ | 7/8 [08:42<01:14, 74.56s/it]
|
||||||
|
100%|██████████| 8/8 [09:56<00:00, 74.51s/it]
|
||||||
|
100%|██████████| 8/8 [09:56<00:00, 74.62s/it]
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 1: generating actions ...
|
||||||
|
>>> Step 1: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 2: generating actions ...
|
||||||
|
>>> Step 2: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 3: generating actions ...
|
||||||
|
>>> Step 3: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 4: generating actions ...
|
||||||
|
>>> Step 4: interacting with world model ...
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
>>> Step 5: generating actions ...
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
>>> Step 5: interacting with world model ...
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case1/unitree_z1_dual_arm_cleanup_pencils_case1.mp4",
|
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case1/unitree_z1_dual_arm_cleanup_pencils_case1.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case1/output/inference/0_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case1/output/inference/0_full_fs4.mp4",
|
||||||
"psnr": 38.269577028444445
|
"psnr": 47.911564449209735
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
|
|||||||
--n_iter 8 \
|
--n_iter 8 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,114 +0,0 @@
|
|||||||
2026-02-11 17:59:40.132715: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 17:59:40.183410: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 17:59:40.183456: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 17:59:40.184784: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 17:59:40.192307: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 17:59:41.105025: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/8 [00:00<?, ?it/s]
|
|
||||||
12%|█▎ | 1/8 [00:23<02:43, 23.41s/it]
|
|
||||||
25%|██▌ | 2/8 [00:46<02:18, 23.00s/it]
|
|
||||||
38%|███▊ | 3/8 [01:08<01:54, 22.94s/it]
|
|
||||||
50%|█████ | 4/8 [01:31<01:31, 22.86s/it]
|
|
||||||
62%|██████▎ | 5/8 [01:54<01:08, 22.82s/it]
|
|
||||||
75%|███████▌ | 6/8 [02:17<00:45, 22.78s/it]
|
|
||||||
88%|████████▊ | 7/8 [02:39<00:22, 22.77s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.75s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.83s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case2/unitree_z1_dual_arm_cleanup_pencils_case2.mp4",
|
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case2/unitree_z1_dual_arm_cleanup_pencils_case2.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case2/output/inference/50_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case2/output/inference/50_full_fs4.mp4",
|
||||||
"psnr": 44.38754096950435
|
"psnr": 48.344571927558974
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
|
|||||||
--n_iter 8 \
|
--n_iter 8 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,114 +0,0 @@
|
|||||||
2026-02-11 18:03:19.373691: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:03:19.423144: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:03:19.423201: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:03:19.424504: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:03:19.431968: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:03:20.342432: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/8 [00:00<?, ?it/s]
|
|
||||||
12%|█▎ | 1/8 [00:23<02:44, 23.45s/it]
|
|
||||||
25%|██▌ | 2/8 [00:46<02:17, 22.99s/it]
|
|
||||||
38%|███▊ | 3/8 [01:09<01:54, 22.94s/it]
|
|
||||||
50%|█████ | 4/8 [01:31<01:31, 22.89s/it]
|
|
||||||
62%|██████▎ | 5/8 [01:54<01:08, 22.84s/it]
|
|
||||||
75%|███████▌ | 6/8 [02:17<00:45, 22.82s/it]
|
|
||||||
88%|████████▊ | 7/8 [02:40<00:22, 22.81s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.79s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.86s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case3/unitree_z1_dual_arm_cleanup_pencils_case3.mp4",
|
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case3/unitree_z1_dual_arm_cleanup_pencils_case3.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case3/output/inference/100_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case3/output/inference/100_full_fs4.mp4",
|
||||||
"psnr": 32.29959078097713
|
"psnr": 41.152374490134825
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
|
|||||||
--n_iter 8 \
|
--n_iter 8 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,114 +0,0 @@
|
|||||||
2026-02-11 18:06:58.863806: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:06:58.913518: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:06:58.913565: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:06:58.914918: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:06:58.922497: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:06:59.840461: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/8 [00:00<?, ?it/s]
|
|
||||||
12%|█▎ | 1/8 [00:23<02:44, 23.47s/it]
|
|
||||||
25%|██▌ | 2/8 [00:46<02:18, 23.01s/it]
|
|
||||||
38%|███▊ | 3/8 [01:09<01:54, 22.94s/it]
|
|
||||||
50%|█████ | 4/8 [01:31<01:31, 22.89s/it]
|
|
||||||
62%|██████▎ | 5/8 [01:54<01:08, 22.85s/it]
|
|
||||||
75%|███████▌ | 6/8 [02:17<00:45, 22.81s/it]
|
|
||||||
88%|████████▊ | 7/8 [02:40<00:22, 22.79s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.77s/it]
|
|
||||||
100%|██████████| 8/8 [03:02<00:00, 22.85s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case4/unitree_z1_dual_arm_cleanup_pencils_case4.mp4",
|
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case4/unitree_z1_dual_arm_cleanup_pencils_case4.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case4/output/inference/200_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case4/output/inference/200_full_fs4.mp4",
|
||||||
"psnr": 45.051241961122535
|
"psnr": 46.025723557253855
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
|
|||||||
--n_iter 8 \
|
--n_iter 8 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,111 +0,0 @@
|
|||||||
2026-02-11 18:10:38.361867: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:10:38.412126: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:10:38.412182: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:10:38.413493: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:10:38.420963: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:10:39.335981: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/7 [00:00<?, ?it/s]
|
|
||||||
14%|█▍ | 1/7 [00:23<02:20, 23.41s/it]
|
|
||||||
29%|██▊ | 2/7 [00:46<01:54, 22.99s/it]
|
|
||||||
43%|████▎ | 3/7 [01:08<01:31, 22.92s/it]
|
|
||||||
57%|█████▋ | 4/7 [01:31<01:08, 22.88s/it]
|
|
||||||
71%|███████▏ | 5/7 [01:54<00:45, 22.82s/it]
|
|
||||||
86%|████████▌ | 6/7 [02:17<00:22, 22.79s/it]
|
|
||||||
100%|██████████| 7/7 [02:39<00:00, 22.75s/it]
|
|
||||||
100%|██████████| 7/7 [02:39<00:00, 22.84s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TiffImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox/case1/unitree_z1_dual_arm_stackbox_case1.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox/case1/unitree_z1_dual_arm_stackbox_case1.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox/case1/output/inference/5_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox/case1/output/inference/5_full_fs4.mp4",
|
||||||
"psnr": 42.717688631296596
|
"psnr": 44.3480149502738
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_stackbox"
|
|||||||
--n_iter 7 \
|
--n_iter 7 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,111 +0,0 @@
|
|||||||
2026-02-11 18:13:57.132827: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:13:57.182101: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:13:57.182156: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:13:57.183471: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:13:57.190931: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:13:58.104923: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/7 [00:00<?, ?it/s]
|
|
||||||
14%|█▍ | 1/7 [00:23<02:20, 23.34s/it]
|
|
||||||
29%|██▊ | 2/7 [00:46<01:54, 22.98s/it]
|
|
||||||
43%|████▎ | 3/7 [01:08<01:31, 22.91s/it]
|
|
||||||
57%|█████▋ | 4/7 [01:31<01:08, 22.87s/it]
|
|
||||||
71%|███████▏ | 5/7 [01:54<00:45, 22.84s/it]
|
|
||||||
86%|████████▌ | 6/7 [02:17<00:22, 22.80s/it]
|
|
||||||
100%|██████████| 7/7 [02:39<00:00, 22.77s/it]
|
|
||||||
100%|██████████| 7/7 [02:39<00:00, 22.84s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TiffImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox/case2/unitree_z1_dual_arm_stackbox_case2.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox/case2/unitree_z1_dual_arm_stackbox_case2.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox/case2/output/inference/15_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox/case2/output/inference/15_full_fs4.mp4",
|
||||||
"psnr": 44.90750363879194
|
"psnr": 39.867728254007716
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_stackbox"
|
|||||||
--n_iter 7 \
|
--n_iter 7 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,111 +0,0 @@
|
|||||||
2026-02-11 18:17:16.023670: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:17:16.073206: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:17:16.073251: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:17:16.074552: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:17:16.082033: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:17:16.997362: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/7 [00:00<?, ?it/s]
|
|
||||||
14%|█▍ | 1/7 [00:23<02:20, 23.41s/it]
|
|
||||||
29%|██▊ | 2/7 [00:46<01:55, 23.03s/it]
|
|
||||||
43%|████▎ | 3/7 [01:09<01:31, 22.95s/it]
|
|
||||||
57%|█████▋ | 4/7 [01:31<01:08, 22.91s/it]
|
|
||||||
71%|███████▏ | 5/7 [01:54<00:45, 22.87s/it]
|
|
||||||
86%|████████▌ | 6/7 [02:17<00:22, 22.84s/it]
|
|
||||||
100%|██████████| 7/7 [02:40<00:00, 22.82s/it]
|
|
||||||
100%|██████████| 7/7 [02:40<00:00, 22.89s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TiffImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox/case3/unitree_z1_dual_arm_stackbox_case3.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox/case3/unitree_z1_dual_arm_stackbox_case3.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox/case3/output/inference/25_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox/case3/output/inference/25_full_fs4.mp4",
|
||||||
"psnr": 39.63695040491171
|
"psnr": 39.19101039445159
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_stackbox"
|
|||||||
--n_iter 7 \
|
--n_iter 7 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,111 +0,0 @@
|
|||||||
2026-02-11 18:20:35.210324: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:20:35.259487: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:20:35.259530: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:20:35.260816: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:20:35.268252: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:20:36.181189: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/7 [00:00<?, ?it/s]
|
|
||||||
14%|█▍ | 1/7 [00:23<02:20, 23.43s/it]
|
|
||||||
29%|██▊ | 2/7 [00:46<01:55, 23.03s/it]
|
|
||||||
43%|████▎ | 3/7 [01:09<01:31, 22.96s/it]
|
|
||||||
57%|█████▋ | 4/7 [01:31<01:08, 22.92s/it]
|
|
||||||
71%|███████▏ | 5/7 [01:54<00:45, 22.89s/it]
|
|
||||||
86%|████████▌ | 6/7 [02:17<00:22, 22.86s/it]
|
|
||||||
100%|██████████| 7/7 [02:40<00:00, 22.84s/it]
|
|
||||||
100%|██████████| 7/7 [02:40<00:00, 22.91s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SunImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TgaImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing TiffImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox/case4/unitree_z1_dual_arm_stackbox_case4.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox/case4/unitree_z1_dual_arm_stackbox_case4.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox/case4/output/inference/35_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox/case4/output/inference/35_full_fs4.mp4",
|
||||||
"psnr": 42.34177660061245
|
"psnr": 40.29563315341769
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_stackbox"
|
|||||||
--n_iter 7 \
|
--n_iter 7 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,16 +1,13 @@
|
|||||||
2026-02-11 18:23:54.635983: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
2026-02-18 18:49:49.117856: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
2026-02-11 18:23:54.685542: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
2026-02-18 18:49:49.165270: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
2026-02-11 18:23:54.685587: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
2026-02-18 18:49:49.165322: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
2026-02-11 18:23:54.686907: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
2026-02-18 18:49:49.166382: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
2026-02-11 18:23:54.694405: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
2026-02-18 18:49:49.173299: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
2026-02-11 18:23:55.620959: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
2026-02-18 18:49:50.090214: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
Global seed set to 123
|
Global seed set to 123
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
>>> Prepared model loaded.
|
>>> Prepared model loaded.
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
INFO:root:***** Configing Data *****
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
@@ -29,45 +26,27 @@ INFO:root:***** Configing Data *****
|
|||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
>>> Dataset is successfully loaded ...
|
>>> Dataset is successfully loaded ...
|
||||||
✓ KV fused: 66 attention layers
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
>>> Generate 16 frames under each generation ...
|
>>> Generate 16 frames under each generation ...
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-18:50:03] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
9%|▉ | 1/11 [00:15<02:38, 15.88s/it]>>> Step 0: generating actions ...
|
9%|▉ | 1/11 [00:15<02:38, 15.88s/it]>>> Step 0: generating actions ...
|
||||||
>>> Step 0: interacting with world model ...
|
>>> Step 0: interacting with world model ...
|
||||||
36%|███▋ | 4/11 [01:31<02:40, 22.86s/it]
|
|
||||||
45%|████▌ | 5/11 [01:54<02:16, 22.83s/it]
|
|
||||||
55%|█████▍ | 6/11 [02:17<01:54, 22.80s/it]
|
|
||||||
64%|██████▎ | 7/11 [02:39<01:31, 22.79s/it]
|
|
||||||
73%|███████▎ | 8/11 [03:02<01:08, 22.79s/it]
|
|
||||||
82%|████████▏ | 9/11 [03:25<00:45, 22.78s/it]
|
|
||||||
91%|█████████ | 10/11 [03:48<00:22, 22.76s/it]
|
|
||||||
100%|██████████| 11/11 [04:10<00:00, 22.75s/it]
|
|
||||||
100%|██████████| 11/11 [04:10<00:00, 22.82s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
>>> Step 1: generating actions ...
|
>>> Step 1: generating actions ...
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
@@ -117,7 +96,37 @@ DEBUG:PIL.Image:Importing WmfImagePlugin
|
|||||||
DEBUG:PIL.Image:Importing WebPImagePlugin
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
DEBUG:PIL.Image:Importing WmfImagePlugin
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XbmImagePlugin
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
|
||||||
|
18%|█▊ | 2/11 [00:31<02:21, 15.71s/it]
|
||||||
|
27%|██▋ | 3/11 [00:47<02:06, 15.86s/it]
|
||||||
|
36%|███▋ | 4/11 [01:03<01:51, 15.90s/it]
|
||||||
|
45%|████▌ | 5/11 [01:19<01:36, 16.06s/it]
|
||||||
|
55%|█████▍ | 6/11 [01:35<01:19, 15.98s/it]
|
||||||
|
64%|██████▎ | 7/11 [01:51<01:04, 16.09s/it]
|
||||||
|
73%|███████▎ | 8/11 [02:08<00:48, 16.08s/it]
|
||||||
|
82%|████████▏ | 9/11 [02:24<00:32, 16.16s/it]
|
||||||
|
91%|█████████ | 10/11 [02:40<00:16, 16.13s/it]
|
||||||
|
100%|██████████| 11/11 [02:56<00:00, 16.09s/it]
|
||||||
|
100%|██████████| 11/11 [02:56<00:00, 16.04s/it]
|
||||||
|
>>> Step 1: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 2: generating actions ...
|
||||||
|
>>> Step 2: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 3: generating actions ...
|
||||||
|
>>> Step 3: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 4: generating actions ...
|
||||||
|
>>> Step 4: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 5: generating actions ...
|
||||||
|
>>> Step 5: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 6: generating actions ...
|
||||||
|
>>> Step 6: interacting with world model ...
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
>>> Step 7: generating actions ...
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
>>> Step 7: interacting with world model ...
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case1/unitree_z1_dual_arm_stackbox_v2_case1.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case1/unitree_z1_dual_arm_stackbox_v2_case1.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case1/output/inference/5_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case1/output/inference/5_full_fs4.mp4",
|
||||||
"psnr": 26.683000215343522
|
"psnr": 27.62636266067224
|
||||||
}
|
}
|
||||||
@@ -1,123 +0,0 @@
|
|||||||
2026-02-11 18:28:48.801743: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:28:48.852069: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:28:48.852128: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:28:48.853466: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:28:48.861133: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:28:49.784354: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
|
||||||
9%|▉ | 1/11 [00:23<03:56, 23.65s/it]
|
|
||||||
18%|█▊ | 2/11 [00:46<03:28, 23.13s/it]
|
|
||||||
27%|██▋ | 3/11 [01:09<03:04, 23.02s/it]
|
|
||||||
36%|███▋ | 4/11 [01:32<02:40, 22.96s/it]
|
|
||||||
45%|████▌ | 5/11 [01:55<02:17, 22.92s/it]
|
|
||||||
55%|█████▍ | 6/11 [02:17<01:54, 22.88s/it]
|
|
||||||
64%|██████▎ | 7/11 [02:40<01:31, 22.84s/it]
|
|
||||||
73%|███████▎ | 8/11 [03:03<01:08, 22.81s/it]
|
|
||||||
82%|████████▏ | 9/11 [03:26<00:45, 22.81s/it]
|
|
||||||
91%|█████████ | 10/11 [03:48<00:22, 22.80s/it]
|
|
||||||
100%|██████████| 11/11 [04:11<00:00, 22.80s/it]
|
|
||||||
100%|██████████| 11/11 [04:11<00:00, 22.88s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case2/unitree_z1_dual_arm_stackbox_v2_case2.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case2/unitree_z1_dual_arm_stackbox_v2_case2.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case2/output/inference/15_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case2/output/inference/15_full_fs4.mp4",
|
||||||
"psnr": 27.46347145461597
|
"psnr": 33.90444714332389
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_stackbox_v2"
|
|||||||
--n_iter 11 \
|
--n_iter 11 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,123 +0,0 @@
|
|||||||
2026-02-11 18:33:43.119091: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:33:43.169099: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:33:43.169143: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:33:43.170444: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:33:43.177944: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:33:44.102499: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
|
||||||
9%|▉ | 1/11 [00:23<03:53, 23.36s/it]
|
|
||||||
18%|█▊ | 2/11 [00:46<03:26, 22.99s/it]
|
|
||||||
27%|██▋ | 3/11 [01:08<03:03, 22.93s/it]
|
|
||||||
36%|███▋ | 4/11 [01:31<02:40, 22.87s/it]
|
|
||||||
45%|████▌ | 5/11 [01:54<02:17, 22.85s/it]
|
|
||||||
55%|█████▍ | 6/11 [02:17<01:54, 22.80s/it]
|
|
||||||
64%|██████▎ | 7/11 [02:40<01:31, 22.79s/it]
|
|
||||||
73%|███████▎ | 8/11 [03:02<01:08, 22.78s/it]
|
|
||||||
82%|████████▏ | 9/11 [03:25<00:45, 22.76s/it]
|
|
||||||
91%|█████████ | 10/11 [03:48<00:22, 22.74s/it]
|
|
||||||
100%|██████████| 11/11 [04:10<00:00, 22.73s/it]
|
|
||||||
100%|██████████| 11/11 [04:10<00:00, 22.81s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case3/unitree_z1_dual_arm_stackbox_v2_case3.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case3/unitree_z1_dual_arm_stackbox_v2_case3.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case3/output/inference/25_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case3/output/inference/25_full_fs4.mp4",
|
||||||
"psnr": 28.604047286947512
|
"psnr": 34.50192428908007
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_stackbox_v2"
|
|||||||
--n_iter 11 \
|
--n_iter 11 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,16 +1,13 @@
|
|||||||
2026-02-11 18:38:37.252690: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
2026-02-18 18:54:56.403136: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
||||||
2026-02-11 18:38:37.301897: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
2026-02-18 18:54:56.451144: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
||||||
2026-02-11 18:38:37.301950: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
2026-02-18 18:54:56.451189: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
||||||
2026-02-11 18:38:37.303254: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
2026-02-18 18:54:56.452312: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
||||||
2026-02-11 18:38:37.310679: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
2026-02-18 18:54:56.459281: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
||||||
2026-02-11 18:38:38.237893: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
2026-02-18 18:54:57.381032: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
||||||
Global seed set to 123
|
Global seed set to 123
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
||||||
>>> Prepared model loaded.
|
>>> Prepared model loaded.
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
INFO:root:***** Configing Data *****
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
>>> unitree_z1_stackbox: 1 data samples loaded.
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
>>> unitree_z1_stackbox: data stats loaded.
|
||||||
@@ -29,16 +26,124 @@ INFO:root:***** Configing Data *****
|
|||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
>>> unitree_g1_pack_camera: normalizer initiated.
|
||||||
>>> Dataset is successfully loaded ...
|
>>> Dataset is successfully loaded ...
|
||||||
✓ KV fused: 66 attention layers
|
✓ KV fused: 66 attention layers
|
||||||
|
TRT output 'y': [1, 4, 16, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_0': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
TRT output 'hs_a_1': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_2': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_3': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_4': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_5': [1, 16, 1280, 5, 8] torch.float32
|
||||||
|
TRT output 'hs_a_6': [1, 16, 1280, 10, 16] torch.float32
|
||||||
|
TRT output 'hs_a_7': [1, 16, 640, 20, 32] torch.float32
|
||||||
|
TRT output 'hs_a_8': [1, 16, 320, 40, 64] torch.float32
|
||||||
|
>>> TRT backbone loaded from /home/qhy/unifolm-world-model-action/scripts/evaluation/../../trt_engines/video_backbone.engine
|
||||||
>>> Generate 16 frames under each generation ...
|
>>> Generate 16 frames under each generation ...
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
DEBUG:h5py._conv:Creating converter from 3 to 5
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
||||||
|
|
||||||
0%| | 0/11 [00:00<?, ?it/s]
|
0%| | 0/11 [00:00<?, ?it/s][02/18/2026-18:55:10] [TRT] [W] Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
|
||||||
|
|
||||||
9%|▉ | 1/11 [00:16<02:45, 16.53s/it]>>> Step 0: generating actions ...
|
9%|▉ | 1/11 [00:16<02:45, 16.53s/it]>>> Step 0: generating actions ...
|
||||||
>>> Step 0: interacting with world model ...
|
>>> Step 0: interacting with world model ...
|
||||||
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
>>> Step 1: generating actions ...
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BlpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BmpImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing CurImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing DdsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing EpsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FliImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FpxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing FtexImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GbrImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GifImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IcoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing ImtImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing IptcImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing JpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MicImagePlugin
|
||||||
|
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpegImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MpoImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing MspImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PalmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PcxImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PdfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PixarImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PngImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing PsdImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing QoiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SgiImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SpiderImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing SunImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TgaImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing TiffImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WebPImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing WmfImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XbmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XpmImagePlugin
|
||||||
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
DEBUG:PIL.Image:Importing XVThumbImagePlugin
|
||||||
|
|
||||||
18%|█▊ | 2/11 [00:33<02:28, 16.52s/it]
|
18%|█▊ | 2/11 [00:33<02:28, 16.52s/it]
|
||||||
@@ -68,56 +173,7 @@ DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
>>> Step 6: generating actions ...
|
>>> Step 6: generating actions ...
|
||||||
>>> Step 6: interacting with world model ...
|
>>> Step 6: interacting with world model ...
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
>>> Step 7: generating actions ...
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
>>> Step 7: interacting with world model ...
|
||||||
DEBUG:PIL.Image:Importing SgiImagePlugin
|
>>>>>>>>>>>>>>>>>>>>>>>>
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case4/unitree_z1_dual_arm_stackbox_v2_case4.mp4",
|
"gt_video": "unitree_z1_dual_arm_stackbox_v2/case4/unitree_z1_dual_arm_stackbox_v2_case4.mp4",
|
||||||
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case4/output/inference/35_full_fs4.mp4",
|
"pred_video": "unitree_z1_dual_arm_stackbox_v2/case4/output/inference/35_full_fs4.mp4",
|
||||||
"psnr": 25.578498826379903
|
"psnr": 25.49270910031428
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_dual_arm_stackbox_v2"
|
|||||||
--n_iter 11 \
|
--n_iter 11 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,126 +0,0 @@
|
|||||||
2026-02-11 18:43:31.592464: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:43:31.641865: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:43:31.641908: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:43:31.643209: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:43:31.650663: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:43:32.564662: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/12 [00:00<?, ?it/s]
|
|
||||||
8%|▊ | 1/12 [00:23<04:17, 23.41s/it]
|
|
||||||
17%|█▋ | 2/12 [00:46<03:50, 23.03s/it]
|
|
||||||
25%|██▌ | 3/12 [01:09<03:26, 22.97s/it]
|
|
||||||
33%|███▎ | 4/12 [01:31<03:03, 22.92s/it]
|
|
||||||
42%|████▏ | 5/12 [01:54<02:40, 22.88s/it]
|
|
||||||
50%|█████ | 6/12 [02:17<02:17, 22.84s/it]
|
|
||||||
58%|█████▊ | 7/12 [02:40<01:54, 22.80s/it]
|
|
||||||
67%|██████▋ | 8/12 [03:02<01:31, 22.78s/it]
|
|
||||||
75%|███████▌ | 9/12 [03:25<01:08, 22.78s/it]
|
|
||||||
83%|████████▎ | 10/12 [03:48<00:45, 22.78s/it]
|
|
||||||
92%|█████████▏| 11/12 [04:11<00:22, 22.77s/it]
|
|
||||||
100%|██████████| 12/12 [04:34<00:00, 22.77s/it]
|
|
||||||
100%|██████████| 12/12 [04:34<00:00, 22.83s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 11: generating actions ...
|
|
||||||
>>> Step 11: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_stackbox/case1/unitree_z1_stackbox_case1.mp4",
|
"gt_video": "unitree_z1_stackbox/case1/unitree_z1_stackbox_case1.mp4",
|
||||||
"pred_video": "unitree_z1_stackbox/case1/output/inference/5_full_fs4.mp4",
|
"pred_video": "unitree_z1_stackbox/case1/output/inference/5_full_fs4.mp4",
|
||||||
"psnr": 46.05271283048069
|
"psnr": 42.83913947323794
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_stackbox"
|
|||||||
--n_iter 12 \
|
--n_iter 12 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,126 +0,0 @@
|
|||||||
2026-02-11 18:48:44.235405: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:48:44.285138: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:48:44.285181: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:48:44.286531: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:48:44.294141: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:48:45.209453: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/12 [00:00<?, ?it/s]
|
|
||||||
8%|▊ | 1/12 [00:23<04:17, 23.37s/it]
|
|
||||||
17%|█▋ | 2/12 [00:46<03:49, 22.97s/it]
|
|
||||||
25%|██▌ | 3/12 [01:08<03:26, 22.91s/it]
|
|
||||||
33%|███▎ | 4/12 [01:31<03:02, 22.86s/it]
|
|
||||||
42%|████▏ | 5/12 [01:54<02:39, 22.82s/it]
|
|
||||||
50%|█████ | 6/12 [02:17<02:16, 22.81s/it]
|
|
||||||
58%|█████▊ | 7/12 [02:39<01:53, 22.79s/it]
|
|
||||||
67%|██████▋ | 8/12 [03:02<01:31, 22.78s/it]
|
|
||||||
75%|███████▌ | 9/12 [03:25<01:08, 22.76s/it]
|
|
||||||
83%|████████▎ | 10/12 [03:48<00:45, 22.75s/it]
|
|
||||||
92%|█████████▏| 11/12 [04:10<00:22, 22.74s/it]
|
|
||||||
100%|██████████| 12/12 [04:33<00:00, 22.72s/it]
|
|
||||||
100%|██████████| 12/12 [04:33<00:00, 22.80s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 11: generating actions ...
|
|
||||||
>>> Step 11: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_stackbox/case2/unitree_z1_stackbox_case2.mp4",
|
"gt_video": "unitree_z1_stackbox/case2/unitree_z1_stackbox_case2.mp4",
|
||||||
"pred_video": "unitree_z1_stackbox/case2/output/inference/15_full_fs4.mp4",
|
"pred_video": "unitree_z1_stackbox/case2/output/inference/15_full_fs4.mp4",
|
||||||
"psnr": 38.94694381287429
|
"psnr": 48.64571989587276
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_stackbox"
|
|||||||
--n_iter 12 \
|
--n_iter 12 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,126 +0,0 @@
|
|||||||
2026-02-11 18:53:57.068615: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:53:57.118271: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:53:57.118312: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:53:57.119665: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:53:57.127266: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:53:58.042116: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/12 [00:00<?, ?it/s]
|
|
||||||
8%|▊ | 1/12 [00:23<04:17, 23.43s/it]
|
|
||||||
17%|█▋ | 2/12 [00:46<03:50, 23.02s/it]
|
|
||||||
25%|██▌ | 3/12 [01:09<03:26, 22.96s/it]
|
|
||||||
33%|███▎ | 4/12 [01:31<03:03, 22.92s/it]
|
|
||||||
42%|████▏ | 5/12 [01:54<02:40, 22.87s/it]
|
|
||||||
50%|█████ | 6/12 [02:17<02:17, 22.85s/it]
|
|
||||||
58%|█████▊ | 7/12 [02:40<01:54, 22.83s/it]
|
|
||||||
67%|██████▋ | 8/12 [03:03<01:31, 22.80s/it]
|
|
||||||
75%|███████▌ | 9/12 [03:25<01:08, 22.78s/it]
|
|
||||||
83%|████████▎ | 10/12 [03:48<00:45, 22.77s/it]
|
|
||||||
92%|█████████▏| 11/12 [04:11<00:22, 22.76s/it]
|
|
||||||
100%|██████████| 12/12 [04:33<00:00, 22.75s/it]
|
|
||||||
100%|██████████| 12/12 [04:33<00:00, 22.83s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 11: generating actions ...
|
|
||||||
>>> Step 11: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_stackbox/case3/unitree_z1_stackbox_case3.mp4",
|
"gt_video": "unitree_z1_stackbox/case3/unitree_z1_stackbox_case3.mp4",
|
||||||
"pred_video": "unitree_z1_stackbox/case3/output/inference/25_full_fs4.mp4",
|
"pred_video": "unitree_z1_stackbox/case3/output/inference/25_full_fs4.mp4",
|
||||||
"psnr": 49.489774674892764
|
"psnr": 45.127553229898034
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_stackbox"
|
|||||||
--n_iter 12 \
|
--n_iter 12 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
@@ -1,126 +0,0 @@
|
|||||||
2026-02-11 18:59:09.688302: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
|
|
||||||
2026-02-11 18:59:09.737473: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
|
||||||
2026-02-11 18:59:09.737518: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
|
||||||
2026-02-11 18:59:09.738835: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
|
||||||
2026-02-11 18:59:09.746322: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
|
|
||||||
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
|
||||||
2026-02-11 18:59:10.660940: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
|
||||||
Global seed set to 123
|
|
||||||
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
|
|
||||||
>>> Prepared model loaded.
|
|
||||||
>>> Diffusion backbone (model.model) converted to FP16.
|
|
||||||
>>> Projectors (image_proj_model, state_projector, action_projector) converted to FP16.
|
|
||||||
>>> Encoders (cond_stage_model, embedder) converted to FP16.
|
|
||||||
INFO:root:***** Configing Data *****
|
|
||||||
>>> unitree_z1_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded.
|
|
||||||
>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated.
|
|
||||||
>>> unitree_g1_pack_camera: 1 data samples loaded.
|
|
||||||
>>> unitree_g1_pack_camera: data stats loaded.
|
|
||||||
>>> unitree_g1_pack_camera: normalizer initiated.
|
|
||||||
>>> Dataset is successfully loaded ...
|
|
||||||
✓ KV fused: 66 attention layers
|
|
||||||
>>> Generate 16 frames under each generation ...
|
|
||||||
DEBUG:h5py._conv:Creating converter from 3 to 5
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9
|
|
||||||
DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096
|
|
||||||
|
|
||||||
0%| | 0/12 [00:00<?, ?it/s]
|
|
||||||
8%|▊ | 1/12 [00:23<04:17, 23.39s/it]
|
|
||||||
17%|█▋ | 2/12 [00:46<03:50, 23.01s/it]
|
|
||||||
25%|██▌ | 3/12 [01:09<03:26, 22.96s/it]
|
|
||||||
33%|███▎ | 4/12 [01:31<03:03, 22.92s/it]
|
|
||||||
42%|████▏ | 5/12 [01:54<02:40, 22.86s/it]
|
|
||||||
50%|█████ | 6/12 [02:17<02:16, 22.82s/it]
|
|
||||||
58%|█████▊ | 7/12 [02:40<01:53, 22.79s/it]
|
|
||||||
67%|██████▋ | 8/12 [03:02<01:31, 22.77s/it]
|
|
||||||
75%|███████▌ | 9/12 [03:25<01:08, 22.77s/it]
|
|
||||||
83%|████████▎ | 10/12 [03:48<00:45, 22.78s/it]
|
|
||||||
92%|█████████▏| 11/12 [04:11<00:22, 22.77s/it]
|
|
||||||
100%|██████████| 12/12 [04:33<00:00, 22.77s/it]
|
|
||||||
100%|██████████| 12/12 [04:33<00:00, 22.83s/it]
|
|
||||||
>>> Step 0: generating actions ...
|
|
||||||
>>> Step 0: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 1: generating actions ...
|
|
||||||
>>> Step 1: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 2: generating actions ...
|
|
||||||
>>> Step 2: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 3: generating actions ...
|
|
||||||
>>> Step 3: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 4: generating actions ...
|
|
||||||
>>> Step 4: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 5: generating actions ...
|
|
||||||
>>> Step 5: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 6: generating actions ...
|
|
||||||
>>> Step 6: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 7: generating actions ...
|
|
||||||
>>> Step 7: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 8: generating actions ...
|
|
||||||
>>> Step 8: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 9: generating actions ...
|
|
||||||
>>> Step 9: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 10: generating actions ...
|
|
||||||
>>> Step 10: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
>>> Step 11: generating actions ...
|
|
||||||
>>> Step 11: interacting with world model ...
|
|
||||||
>>>>>>>>>>>>>>>>>>>>>>>>
|
|
||||||
DEBUG:PIL.Image:Importing BlpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BmpImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing BufrStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing CurImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing DdsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing EpsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FitsStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FliImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing FpxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing FtexImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GbrImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GifImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing GribStubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Hdf5StubImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcnsImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IcoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing ImtImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing IptcImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing JpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing Jpeg2KImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing McIdasImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MicImagePlugin
|
|
||||||
DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile'
|
|
||||||
DEBUG:PIL.Image:Importing MpegImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MpoImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing MspImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PalmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PcxImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PdfImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PixarImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PngImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PpmImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing PsdImagePlugin
|
|
||||||
DEBUG:PIL.Image:Importing QoiImagePlugin
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"gt_video": "unitree_z1_stackbox/case4/unitree_z1_stackbox_case4.mp4",
|
"gt_video": "unitree_z1_stackbox/case4/unitree_z1_stackbox_case4.mp4",
|
||||||
"pred_video": "unitree_z1_stackbox/case4/output/inference/35_full_fs4.mp4",
|
"pred_video": "unitree_z1_stackbox/case4/output/inference/35_full_fs4.mp4",
|
||||||
"psnr": 47.18724378194084
|
"psnr": 50.642542240144444
|
||||||
}
|
}
|
||||||
@@ -20,6 +20,5 @@ dataset="unitree_z1_stackbox"
|
|||||||
--n_iter 12 \
|
--n_iter 12 \
|
||||||
--timestep_spacing 'uniform_trailing' \
|
--timestep_spacing 'uniform_trailing' \
|
||||||
--guidance_rescale 0.7 \
|
--guidance_rescale 0.7 \
|
||||||
--perframe_ae \
|
--perframe_ae
|
||||||
--fast_policy_no_decode
|
|
||||||
} 2>&1 | tee "${res_dir}/output.log"
|
} 2>&1 | tee "${res_dir}/output.log"
|
||||||
|
|||||||
Reference in New Issue
Block a user