保存的优化

attention.py — 3处改动：
  1. __init__ 添加 _kv_fused = False 标志
  2.新增 fuse_kv() 方法：将 to_k + to_v → to_kv，同时处理 _ip/_as/_aa 辅助 KV 对
  2. bmm_forward 两个分支加_kv_fused 判断，用to_kv().chunk(2, dim=-1) 替代分别调用

.claude/settings.local.json

@@ -4,7 +4,12 @@
       "Bash(conda env list:*)",
       "Bash(mamba env:*)",
       "Bash(micromamba env list:*)",
-      "Bash(echo:*)"
+      "Bash(echo:*)",
+      "Bash(git show:*)",
+      "Bash(nvidia-smi:*)",
+      "Bash(conda activate unifolm-wma)",
+      "Bash(conda info:*)",
+      "Bash(direnv allow:*)"
     ]
   }
 }

.envrc

@@ -0,0 +1,2 @@
+eval "$(conda shell.bash hook 2>/dev/null)"
+conda activate unifolm-wma

.gitignore

@@ -130,4 +130,7 @@ Experiment/log
 
 *.ckpt
 
-*.0
+*.0
+ckpts/unifolm_wma_dual.ckpt.prepared.pt
+trt_engines/video_backbone.engine
+trt_engines/video_backbone.onnx

record.md

@@ -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） │
+  └───────────────────────────────────┴────────────┴────────────────────────────────────────────────────────┘

run_all_case.sh

@@ -0,0 +1,114 @@
+#!/bin/bash
+
+# 自动执行所有场景的所有case
+# 总共5个场景，每个场景4个case，共20个case
+# 设置环境变量（离线模式）
+export HF_HUB_OFFLINE=1
+export TRANSFORMERS_OFFLINE=1
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 定义所有场景
+SCENARIOS=(
+    "unitree_g1_pack_camera"
+    "unitree_z1_dual_arm_cleanup_pencils"
+    "unitree_z1_dual_arm_stackbox"
+    "unitree_z1_dual_arm_stackbox_v2"
+    "unitree_z1_stackbox"
+)
+
+# 定义case数量
+CASES=(1 2 3 4)
+
+# 记录开始时间
+START_TIME=$(date +%s)
+LOG_FILE="run_all_cases_$(date +%Y%m%d_%H%M%S).log"
+
+echo -e "${BLUE}========================================${NC}"
+echo -e "${BLUE}开始执行所有场景的case${NC}"
+echo -e "${BLUE}总共: ${#SCENARIOS[@]} 个场景 x ${#CASES[@]} 个case = $((${#SCENARIOS[@]} * ${#CASES[@]})) 个任务${NC}"
+echo -e "${BLUE}日志文件: ${LOG_FILE}${NC}"
+echo -e "${BLUE}========================================${NC}"
+echo ""
+
+# 初始化计数器
+TOTAL_CASES=$((${#SCENARIOS[@]} * ${#CASES[@]}))
+CURRENT_CASE=0
+SUCCESS_COUNT=0
+FAIL_COUNT=0
+
+# 记录失败的case
+declare -a FAILED_CASES
+
+# 遍历所有场景
+for scenario in "${SCENARIOS[@]}"; do
+    echo -e "${YELLOW}>>> 场景: ${scenario}${NC}"
+
+    # 遍历所有case
+    for case_num in "${CASES[@]}"; do
+        CURRENT_CASE=$((CURRENT_CASE + 1))
+        case_dir="${scenario}/case${case_num}"
+        script_path="${case_dir}/run_world_model_interaction.sh"
+
+        echo -e "${BLUE}[${CURRENT_CASE}/${TOTAL_CASES}] 执行: ${case_dir}${NC}"
+
+        # 检查脚本是否存在
+        if [ ! -f "${script_path}" ]; then
+            echo -e "${RED}错误: 脚本不存在 ${script_path}${NC}"
+            FAIL_COUNT=$((FAIL_COUNT + 1))
+            FAILED_CASES+=("${case_dir} (脚本不存在)")
+            continue
+        fi
+
+        # 执行脚本
+        echo "开始时间: $(date '+%Y-%m-%d %H:%M:%S')"
+
+        if bash "${script_path}" >> "${LOG_FILE}" 2>&1; then
+            echo -e "${GREEN}✓ 成功: ${case_dir}${NC}"
+            SUCCESS_COUNT=$((SUCCESS_COUNT + 1))
+        else
+            echo -e "${RED}✗ 失败: ${case_dir}${NC}"
+            FAIL_COUNT=$((FAIL_COUNT + 1))
+            FAILED_CASES+=("${case_dir}")
+        fi
+
+        echo "结束时间: $(date '+%Y-%m-%d %H:%M:%S')"
+        echo ""
+    done
+
+    echo ""
+done
+
+# 计算总耗时
+END_TIME=$(date +%s)
+DURATION=$((END_TIME - START_TIME))
+HOURS=$((DURATION / 3600))
+MINUTES=$(((DURATION % 3600) / 60))
+SECONDS=$((DURATION % 60))
+
+# 输出总结
+echo -e "${BLUE}========================================${NC}"
+echo -e "${BLUE}执行完成！${NC}"
+echo -e "${BLUE}========================================${NC}"
+echo -e "总任务数: ${TOTAL_CASES}"
+echo -e "${GREEN}成功: ${SUCCESS_COUNT}${NC}"
+echo -e "${RED}失败: ${FAIL_COUNT}${NC}"
+echo -e "总耗时: ${HOURS}小时 ${MINUTES}分钟 ${SECONDS}秒"
+echo -e "详细日志: ${LOG_FILE}"
+echo ""
+
+# 如果有失败的case，列出来
+if [ ${FAIL_COUNT} -gt 0 ]; then
+    echo -e "${RED}失败的case列表:${NC}"
+    for failed_case in "${FAILED_CASES[@]}"; do
+        echo -e "${RED}  - ${failed_case}${NC}"
+    done
+    echo ""
+fi
+
+echo -e "${BLUE}========================================${NC}"

run_all_cases_20260218_190150.log

@@ -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

run_all_psnr.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+cd "$SCRIPT_DIR"
+
+SCENARIOS=(
+    unitree_g1_pack_camera
+    unitree_z1_dual_arm_cleanup_pencils
+    unitree_z1_dual_arm_stackbox
+    unitree_z1_dual_arm_stackbox_v2
+    unitree_z1_stackbox
+)
+
+CASES=(case1 case2 case3 case4)
+
+total=0
+success=0
+fail=0
+
+for scenario in "${SCENARIOS[@]}"; do
+    for case in "${CASES[@]}"; do
+        case_dir="${scenario}/${case}"
+        gt_video="${case_dir}/${scenario}_${case}.mp4"
+        pred_video=$(ls "${case_dir}"/output/inference/*_full_fs*.mp4 2>/dev/null | head -1)
+        output_file="${case_dir}/psnr_result.json"
+
+        total=$((total + 1))
+        echo "=========================================="
+        echo "[${total}/20] ${case_dir}"
+
+        if [ ! -f "$gt_video" ]; then
+            echo "  SKIP: GT video not found: $gt_video"
+            fail=$((fail + 1))
+            continue
+        fi
+        if [ -z "$pred_video" ]; then
+            echo "  SKIP: pred video not found in ${case_dir}/output/inference/"
+            fail=$((fail + 1))
+            continue
+        fi
+
+        echo "  GT:   $gt_video"
+        echo "  Pred: $pred_video"
+        echo "  Out:  $output_file"
+
+        if python3 psnr_score_for_challenge.py \
+            --gt_video "$gt_video" \
+            --pred_video "$pred_video" \
+            --output_file "$output_file"; then
+            success=$((success + 1))
+            echo "  DONE"
+        else
+            fail=$((fail + 1))
+            echo "  FAILED"
+        fi
+    done
+done
+
+echo "=========================================="
+echo "Finished: ${success} success, ${fail} fail, ${total} total"

scripts/evaluation/world_model_interaction.py

@@ -9,6 +9,8 @@ import logging
 import einops
 import warnings
 import imageio
+import atexit
+from concurrent.futures import ThreadPoolExecutor
 
 from pytorch_lightning import seed_everything
 from omegaconf import OmegaConf
@@ -16,8 +18,9 @@ from tqdm import tqdm
 from einops import rearrange, repeat
 from collections import OrderedDict
 from torch import nn
-from eval_utils import populate_queues, log_to_tensorboard
+from eval_utils import populate_queues
 from collections import deque
+from typing import Optional, List, Any
 
 torch.backends.cuda.matmul.allow_tf32 = True
 torch.backends.cudnn.allow_tf32 = True
@@ -153,6 +156,81 @@ def save_results(video: Tensor, filename: str, fps: int = 8) -> None:
                                options={'crf': '10'})
 
 
+# ========== Async I/O ==========
+_io_executor: Optional[ThreadPoolExecutor] = None
+_io_futures: List[Any] = []
+
+
+def _get_io_executor() -> ThreadPoolExecutor:
+    global _io_executor
+    if _io_executor is None:
+        _io_executor = ThreadPoolExecutor(max_workers=2)
+    return _io_executor
+
+
+def _flush_io():
+    """Wait for all pending async I/O to finish."""
+    global _io_futures
+    for fut in _io_futures:
+        try:
+            fut.result()
+        except Exception as e:
+            print(f">>> [async I/O] error: {e}")
+    _io_futures.clear()
+
+
+atexit.register(_flush_io)
+
+
+def _save_results_sync(video_cpu: Tensor, filename: str, fps: int) -> None:
+    """Synchronous save on CPU tensor (runs in background thread)."""
+    video = torch.clamp(video_cpu.float(), -1., 1.)
+    n = video.shape[0]
+    video = video.permute(2, 0, 1, 3, 4)
+    frame_grids = [
+        torchvision.utils.make_grid(framesheet, nrow=int(n), padding=0)
+        for framesheet in video
+    ]
+    grid = torch.stack(frame_grids, dim=0)
+    grid = (grid + 1.0) / 2.0
+    grid = (grid * 255).to(torch.uint8).permute(0, 2, 3, 1)
+    torchvision.io.write_video(filename,
+                               grid,
+                               fps=fps,
+                               video_codec='h264',
+                               options={'crf': '10'})
+
+
+def save_results_async(video: Tensor, filename: str, fps: int = 8) -> None:
+    """Submit video saving to background thread pool."""
+    video_cpu = video.detach().cpu()
+    fut = _get_io_executor().submit(_save_results_sync, video_cpu, filename, fps)
+    _io_futures.append(fut)
+
+
+def _log_to_tb_sync(writer, video_cpu: Tensor, tag: str, fps: int) -> None:
+    """Synchronous TensorBoard log on CPU tensor (runs in background thread)."""
+    if video_cpu.dim() == 5:
+        n = video_cpu.shape[0]
+        video = video_cpu.permute(2, 0, 1, 3, 4)
+        frame_grids = [
+            torchvision.utils.make_grid(framesheet, nrow=int(n), padding=0)
+            for framesheet in video
+        ]
+        grid = torch.stack(frame_grids, dim=0)
+        grid = (grid + 1.0) / 2.0
+        grid = grid.unsqueeze(dim=0)
+        writer.add_video(tag, grid, fps=fps)
+
+
+def log_to_tensorboard_async(writer, data: Tensor, tag: str, fps: int = 10) -> None:
+    """Submit TensorBoard logging to background thread pool."""
+    if isinstance(data, torch.Tensor) and data.dim() == 5:
+        data_cpu = data.detach().cpu()
+        fut = _get_io_executor().submit(_log_to_tb_sync, writer, data_cpu, tag, fps)
+        _io_futures.append(fut)
+
+
 def get_init_frame_path(data_dir: str, sample: dict) -> str:
     """Construct the init_frame path from directory and sample metadata.
 
@@ -462,26 +540,56 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
     csv_path = os.path.join(args.prompt_dir, f"{args.dataset}.csv")
     df = pd.read_csv(csv_path)
 
-    # Load config
+    # Load config (always needed for data setup)
     config = OmegaConf.load(args.config)
-    config['model']['params']['wma_config']['params'][
-        'use_checkpoint'] = False
-    model = instantiate_from_config(config.model)
-    model.perframe_ae = args.perframe_ae
-    assert os.path.exists(args.ckpt_path), "Error: checkpoint Not Found!"
-    model = load_model_checkpoint(model, args.ckpt_path)
-    model.eval()
-    print(f'>>> Load pre-trained model ...')
 
-    # Build unnomalizer
+    prepared_path = args.ckpt_path + ".prepared.pt"
+    if os.path.exists(prepared_path):
+        # ---- Fast path: load the fully-prepared model ----
+        print(f">>> Loading prepared model from {prepared_path} ...")
+        model = torch.load(prepared_path,
+                           map_location=f"cuda:{gpu_no}",
+                           weights_only=False,
+                           mmap=True)
+        model.eval()
+        print(f">>> Prepared model loaded.")
+    else:
+        # ---- Normal path: construct + load checkpoint ----
+        config['model']['params']['wma_config']['params'][
+            'use_checkpoint'] = False
+        model = instantiate_from_config(config.model)
+        model.perframe_ae = args.perframe_ae
+
+        assert os.path.exists(args.ckpt_path), "Error: checkpoint Not Found!"
+        model = load_model_checkpoint(model, args.ckpt_path)
+        model.eval()
+        model = model.cuda(gpu_no)
+        print(f'>>> Load pre-trained model ...')
+
+        # Save prepared model for fast loading next time
+        print(f">>> Saving prepared model to {prepared_path} ...")
+        torch.save(model, prepared_path)
+        print(f">>> Prepared model saved ({os.path.getsize(prepared_path) / 1024**3:.1f} GB).")
+
+    # Build normalizer (always needed, independent of model loading path)
     logging.info("***** Configing Data *****")
     data = instantiate_from_config(config.data)
     data.setup()
     print(">>> Dataset is successfully loaded ...")
 
-    model = model.cuda(gpu_no)
     device = get_device_from_parameters(model)
 
+    # Fuse KV projections in attention layers (to_k + to_v → to_kv)
+    from unifolm_wma.modules.attention import CrossAttention
+    kv_count = sum(1 for m in model.modules()
+                   if isinstance(m, CrossAttention) and m.fuse_kv())
+    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
     assert (args.height % 16 == 0) and (
         args.width % 16
@@ -654,31 +762,31 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
                     cond_obs_queues = populate_queues(cond_obs_queues,
                                                       observation)
 
-                # Save the imagen videos for decision-making
+                # Save the imagen videos for decision-making (async)
                 if pred_videos_0 is not None:
                     sample_tag = f"{args.dataset}-vid{sample['videoid']}-dm-fs-{fs}/itr-{itr}"
-                    log_to_tensorboard(writer,
-                                       pred_videos_0,
-                                       sample_tag,
-                                       fps=args.save_fps)
+                    log_to_tensorboard_async(writer,
+                                             pred_videos_0,
+                                             sample_tag,
+                                             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(writer,
-                                   pred_videos_1,
-                                   sample_tag,
-                                   fps=args.save_fps)
+                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(pred_videos_0.cpu(),
-                                 sample_video_file,
-                                 fps=args.save_fps)
+                    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(pred_videos_1.cpu(),
-                             sample_video_file,
-                             fps=args.save_fps)
+                save_results_async(pred_videos_1,
+                                   sample_video_file,
+                                   fps=args.save_fps)
 
                 print('>' * 24)
                 # Collect the result of world-model interactions
@@ -686,12 +794,15 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
 
             full_video = torch.cat(wm_video, dim=2)
             sample_tag = f"{args.dataset}-vid{sample['videoid']}-wd-fs-{fs}/full"
-            log_to_tensorboard(writer,
-                               full_video,
-                               sample_tag,
-                               fps=args.save_fps)
+            log_to_tensorboard_async(writer,
+                                     full_video,
+                                     sample_tag,
+                                     fps=args.save_fps)
             sample_full_video_file = f"{video_save_dir}/../{sample['videoid']}_full_fs{fs}.mp4"
-            save_results(full_video, sample_full_video_file, fps=args.save_fps)
+            save_results_async(full_video, sample_full_video_file, fps=args.save_fps)
+
+    # Wait for all async I/O to complete
+    _flush_io()
 
 
 def get_parser():

scripts/export_trt.py

@@ -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()

src/unifolm_wma/modules/attention.py

@@ -100,6 +100,7 @@ class CrossAttention(nn.Module):
         self.agent_action_context_len = agent_action_context_len
         self._kv_cache = {}
         self._kv_cache_enabled = False
+        self._kv_fused = False
 
         self.cross_attention_scale_learnable = cross_attention_scale_learnable
         if self.image_cross_attention:
@@ -117,6 +118,27 @@ class CrossAttention(nn.Module):
                 self.register_parameter('alpha_caa',
                                         nn.Parameter(torch.tensor(0.)))
 
+    def fuse_kv(self):
+        """Fuse to_k/to_v into to_kv (2 Linear → 1). Works for all layers."""
+        k_w = self.to_k.weight  # (inner_dim, context_dim)
+        v_w = self.to_v.weight
+        self.to_kv = nn.Linear(k_w.shape[1], k_w.shape[0] * 2, bias=False)
+        self.to_kv.weight = nn.Parameter(torch.cat([k_w, v_w], dim=0))
+        del self.to_k, self.to_v
+        if self.image_cross_attention:
+            for suffix in ('_ip', '_as', '_aa'):
+                k_attr = f'to_k{suffix}'
+                v_attr = f'to_v{suffix}'
+                kw = getattr(self, k_attr).weight
+                vw = getattr(self, v_attr).weight
+                fused = nn.Linear(kw.shape[1], kw.shape[0] * 2, bias=False)
+                fused.weight = nn.Parameter(torch.cat([kw, vw], dim=0))
+                setattr(self, f'to_kv{suffix}', fused)
+                delattr(self, k_attr)
+                delattr(self, v_attr)
+        self._kv_fused = True
+        return True
+
     def forward(self, x, context=None, mask=None):
         spatial_self_attn = (context is None)
         k_ip, v_ip, out_ip = None, None, None
@@ -143,19 +165,28 @@ class CrossAttention(nn.Module):
                                     self.agent_action_context_len +
                                     self.text_context_len:, :]
 
-            k = self.to_k(context_ins)
-            v = self.to_v(context_ins)
-            k_ip = self.to_k_ip(context_image)
-            v_ip = self.to_v_ip(context_image)
-            k_as = self.to_k_as(context_agent_state)
-            v_as = self.to_v_as(context_agent_state)
-            k_aa = self.to_k_aa(context_agent_action)
-            v_aa = self.to_v_aa(context_agent_action)
+            if self._kv_fused:
+                k, v = self.to_kv(context_ins).chunk(2, dim=-1)
+                k_ip, v_ip = self.to_kv_ip(context_image).chunk(2, dim=-1)
+                k_as, v_as = self.to_kv_as(context_agent_state).chunk(2, dim=-1)
+                k_aa, v_aa = self.to_kv_aa(context_agent_action).chunk(2, dim=-1)
+            else:
+                k = self.to_k(context_ins)
+                v = self.to_v(context_ins)
+                k_ip = self.to_k_ip(context_image)
+                v_ip = self.to_v_ip(context_image)
+                k_as = self.to_k_as(context_agent_state)
+                v_as = self.to_v_as(context_agent_state)
+                k_aa = self.to_k_aa(context_agent_action)
+                v_aa = self.to_v_aa(context_agent_action)
         else:
             if not spatial_self_attn:
                 context = context[:, :self.text_context_len, :]
-            k = self.to_k(context)
-            v = self.to_v(context)
+            if self._kv_fused:
+                k, v = self.to_kv(context).chunk(2, dim=-1)
+            else:
+                k = self.to_k(context)
+                v = self.to_v(context)
 
         q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h),
                       (q, k, v))
@@ -267,10 +298,14 @@ class CrossAttention(nn.Module):
         elif self.image_cross_attention and not spatial_self_attn:
             if context.shape[1] == self.text_context_len + self.video_length:
                 context_ins, context_image = context[:, :self.text_context_len, :], context[:,self.text_context_len:, :]
-                k = self.to_k(context)
-                v = self.to_v(context)
-                k_ip = self.to_k_ip(context_image)
-                v_ip = self.to_v_ip(context_image)
+                if self._kv_fused:
+                    k, v = self.to_kv(context).chunk(2, dim=-1)
+                    k_ip, v_ip = self.to_kv_ip(context_image).chunk(2, dim=-1)
+                else:
+                    k = self.to_k(context)
+                    v = self.to_v(context)
+                    k_ip = self.to_k_ip(context_image)
+                    v_ip = self.to_v_ip(context_image)
                 k, v = map(_reshape_kv, (k, v))
                 k_ip, v_ip = map(_reshape_kv, (k_ip, v_ip))
                 if use_cache:
@@ -279,12 +314,17 @@ class CrossAttention(nn.Module):
                 context_agent_state = context[:, :self.agent_state_context_len, :]
                 context_ins = context[:, self.agent_state_context_len:self.agent_state_context_len+self.text_context_len, :]
                 context_image = context[:, self.agent_state_context_len+self.text_context_len:, :]
-                k = self.to_k(context_ins)
-                v = self.to_v(context_ins)
-                k_ip = self.to_k_ip(context_image)
-                v_ip = self.to_v_ip(context_image)
-                k_as = self.to_k_as(context_agent_state)
-                v_as = self.to_v_as(context_agent_state)
+                if self._kv_fused:
+                    k, v = self.to_kv(context_ins).chunk(2, dim=-1)
+                    k_ip, v_ip = self.to_kv_ip(context_image).chunk(2, dim=-1)
+                    k_as, v_as = self.to_kv_as(context_agent_state).chunk(2, dim=-1)
+                else:
+                    k = self.to_k(context_ins)
+                    v = self.to_v(context_ins)
+                    k_ip = self.to_k_ip(context_image)
+                    v_ip = self.to_v_ip(context_image)
+                    k_as = self.to_k_as(context_agent_state)
+                    v_as = self.to_v_as(context_agent_state)
                 k, v = map(_reshape_kv, (k, v))
                 k_ip, v_ip = map(_reshape_kv, (k_ip, v_ip))
                 k_as, v_as = map(_reshape_kv, (k_as, v_as))
@@ -296,14 +336,20 @@ class CrossAttention(nn.Module):
                 context_ins = context[:, self.agent_state_context_len+self.agent_action_context_len:self.agent_state_context_len+self.agent_action_context_len+self.text_context_len, :]
                 context_image = context[:, self.agent_state_context_len+self.agent_action_context_len+self.text_context_len:, :]
 
-                k = self.to_k(context_ins)
-                v = self.to_v(context_ins)
-                k_ip = self.to_k_ip(context_image)
-                v_ip = self.to_v_ip(context_image)
-                k_as = self.to_k_as(context_agent_state)
-                v_as = self.to_v_as(context_agent_state)
-                k_aa = self.to_k_aa(context_agent_action)
-                v_aa = self.to_v_aa(context_agent_action)
+                if self._kv_fused:
+                    k, v = self.to_kv(context_ins).chunk(2, dim=-1)
+                    k_ip, v_ip = self.to_kv_ip(context_image).chunk(2, dim=-1)
+                    k_as, v_as = self.to_kv_as(context_agent_state).chunk(2, dim=-1)
+                    k_aa, v_aa = self.to_kv_aa(context_agent_action).chunk(2, dim=-1)
+                else:
+                    k = self.to_k(context_ins)
+                    v = self.to_v(context_ins)
+                    k_ip = self.to_k_ip(context_image)
+                    v_ip = self.to_v_ip(context_image)
+                    k_as = self.to_k_as(context_agent_state)
+                    v_as = self.to_v_as(context_agent_state)
+                    k_aa = self.to_k_aa(context_agent_action)
+                    v_aa = self.to_v_aa(context_agent_action)
 
                 k, v = map(_reshape_kv, (k, v))
                 k_ip, v_ip = map(_reshape_kv, (k_ip, v_ip))
@@ -328,8 +374,11 @@ class CrossAttention(nn.Module):
             if not spatial_self_attn:
                 assert 1 > 2, ">>> ERROR: you should never go into here ..."
                 context = context[:, :self.text_context_len, :]
-            k = self.to_k(context)
-            v = self.to_v(context)
+            if self._kv_fused:
+                k, v = self.to_kv(context).chunk(2, dim=-1)
+            else:
+                k = self.to_k(context)
+                v = self.to_v(context)
             k, v = map(_reshape_kv, (k, v))
             if use_cache:
                 self._kv_cache = {'k': k, 'v': v}

src/unifolm_wma/modules/networks/wma_model.py

@@ -688,6 +688,24 @@ class WMAModel(nn.Module):
         # Context precomputation cache
         self._ctx_cache_enabled = False
         self._ctx_cache = {}
+        self._trt_backbone = None  # TRT engine for video UNet backbone
+        # Reusable CUDA stream for parallel state_unet / action_unet
+        self._state_stream = torch.cuda.Stream()
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+        state.pop('_state_stream', None)
+        return state
+
+    def __setstate__(self, state):
+        self.__dict__.update(state)
+        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,
                 x: Tensor,
@@ -801,56 +819,63 @@ class WMAModel(nn.Module):
             fs_embed = fs_embed.repeat_interleave(repeats=t, dim=0)
             emb = emb + fs_embed
 
-        h = x.type(self.dtype)
-        adapter_idx = 0
-        hs = []
-        hs_a = []
-        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)
-            # 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):
+        if self._trt_backbone is not None:
+            # TRT path: run backbone via TensorRT engine
+            h_in = x.type(self.dtype).contiguous()
+            y, hs_a = self._trt_backbone(h_in, emb.contiguous(), context.contiguous())
+        else:
+            # PyTorch path: original backbone
+            h = x.type(self.dtype)
+            adapter_idx = 0
+            hs = []
+            hs_a = []
+            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)
+                # 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(
-                        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))
+                        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))
 
-        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(
-                    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)
+            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:
             ba, _, _ = x_action.shape
+            ts_state = timesteps[:ba] if b > 1 else timesteps
+            # Run action_unet and state_unet in parallel via CUDA streams
+            s_stream = self._state_stream
+            s_stream.wait_stream(torch.cuda.current_stream())
+            with torch.cuda.stream(s_stream):
+                s_y = self.state_unet(x_state, ts_state, hs_a,
+                                      context_action[:2], **kwargs)
             a_y = self.action_unet(x_action, timesteps[:ba], hs_a,
                                    context_action[:2], **kwargs)
-            # Predict state
-            if b > 1:
-                s_y = self.state_unet(x_state, timesteps[:ba], hs_a,
-                                      context_action[:2], **kwargs)
-            else:
-                s_y = self.state_unet(x_state, timesteps, hs_a,
-                                      context_action[:2], **kwargs)
+            torch.cuda.current_stream().wait_stream(s_stream)
         else:
             a_y = torch.zeros_like(x_action)
             s_y = torch.zeros_like(x_state)

src/unifolm_wma/trt_utils.py

@@ -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

unitree_g1_pack_camera/case1/output.log

@@ -0,0 +1,179 @@
+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 ...
+>>>>>>>>>>>>>>>>>>>>>>>>

unitree_g1_pack_camera/case1/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 35.615362167470806
+}

unitree_g1_pack_camera/case2/output.log

@@ -0,0 +1,179 @@
+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 ...
+>>>>>>>>>>>>>>>>>>>>>>>>

unitree_g1_pack_camera/case2/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 34.61979248212279
+}

unitree_g1_pack_camera/case3/output.log

@@ -0,0 +1,146 @@
+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
+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

unitree_g1_pack_camera/case3/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 37.034952654534486
+}

unitree_g1_pack_camera/case4/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 31.43390896360405
+}

unitree_z1_dual_arm_cleanup_pencils/case2/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 48.344571927558974
+}

unitree_z1_dual_arm_cleanup_pencils/case3/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 41.152374490134825
+}

unitree_z1_dual_arm_cleanup_pencils/case4/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 46.025723557253855
+}

unitree_z1_dual_arm_stackbox/case1/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 44.3480149502738
+}

unitree_z1_dual_arm_stackbox/case2/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 39.867728254007716
+}

unitree_z1_dual_arm_stackbox/case3/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 39.19101039445159
+}

unitree_z1_dual_arm_stackbox/case4/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 40.29563315341769
+}

unitree_z1_dual_arm_stackbox_v2/case1/output.log

@@ -1,24 +1,13 @@
-2026-02-10 17:39:22.590654: 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 17:39:22.640645: 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 17:39:22.640689: 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 17:39:22.642010: 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 17:39:22.649530: 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 18:49:49.117856: 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`.
+2026-02-18 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
+2026-02-18 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
+2026-02-18 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
+2026-02-18 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.
-2026-02-10 17:39:23.575804: 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
-INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode
-INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08
-INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08
-AE working on z of shape (1, 4, 32, 32) = 4096 dimensions.
-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 ...
+>>> 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.
@@ -36,13 +25,28 @@ INFO:root:***** Configing Data *****
 >>> 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][02/18/2026-18:50:03] [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 ...
+>>> Step 0: interacting with world model ...
 >>>>>>>>>>>>>>>>>>>>>>>>
 >>> Step 1: generating actions ...
 DEBUG:PIL.Image:Importing BlpImagePlugin
@@ -92,9 +96,7 @@ DEBUG:PIL.Image:Importing WmfImagePlugin
 DEBUG:PIL.Image:Importing WebPImagePlugin
 DEBUG:PIL.Image:Importing WmfImagePlugin
 DEBUG:PIL.Image:Importing XbmImagePlugin
-DEBUG:PIL.Image:Importing XVThumbImagePlugin
-
-  9%|▉         | 1/11 [00:35<05:55, 35.52s/it]
+DEBUG:PIL.Image:Importing XpmImagePlugin
 DEBUG:PIL.Image:Importing XVThumbImagePlugin
 
  18%|█▊        | 2/11 [00:31<02:21, 15.71s/it]
@@ -125,6 +127,6 @@ DEBUG:PIL.Image:Importing XVThumbImagePlugin
 >>> Step 6: generating actions ...
 >>> Step 6: interacting with world model ...
 >>>>>>>>>>>>>>>>>>>>>>>>
->>> Step 7: generating actions ...
->>> Step 7: interacting with world model ...
->>>>>>>>>>>>>>>>>>>>>>>>
+>>> Step 7: generating actions ...
+>>> Step 7: interacting with world model ...
+>>>>>>>>>>>>>>>>>>>>>>>>

unitree_z1_dual_arm_stackbox_v2/case1/psnr_result.json

@@ -1,5 +1,5 @@
 {
-    "gt_video": "/home/qhy/unifolm-world-model-action/unitree_z1_dual_arm_stackbox_v2/case1/unitree_z1_dual_arm_stackbox_v2_case1.mp4",
-    "pred_video": "/home/qhy/unifolm-world-model-action/unitree_z1_dual_arm_stackbox_v2/case1/output/inference/5_full_fs4.mp4",
-    "psnr": 25.12008483689618
+    "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",
+    "psnr": 27.62636266067224
 }

unitree_z1_dual_arm_stackbox_v2/case2/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 33.90444714332389
+}

unitree_z1_dual_arm_stackbox_v2/case3/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 34.50192428908007
+}

unitree_z1_dual_arm_stackbox_v2/case4/output.log

@@ -0,0 +1,179 @@
+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`.
+2026-02-18 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
+2026-02-18 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
+2026-02-18 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
+2026-02-18 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.
+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
+>>> 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][02/18/2026-18:55:10] [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 ...
+>>> 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<02:28, 16.52s/it]
+ 27%|██▋       | 3/11 [00:49<02:12, 16.53s/it]
+ 36%|███▋      | 4/11 [01:06<01:56, 16.64s/it]
+ 45%|████▌     | 5/11 [01:23<01:40, 16.69s/it]
+ 55%|█████▍    | 6/11 [01:39<01:23, 16.71s/it]
+ 64%|██████▎   | 7/11 [01:56<01:06, 16.68s/it]
+ 73%|███████▎  | 8/11 [02:13<00:50, 16.68s/it]
+ 82%|████████▏ | 9/11 [02:29<00:33, 16.71s/it]
+ 91%|█████████ | 10/11 [02:46<00:16, 16.72s/it]
+100%|██████████| 11/11 [03:03<00:00, 16.69s/it]
+100%|██████████| 11/11 [03:03<00:00, 16.67s/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 ...
+>>>>>>>>>>>>>>>>>>>>>>>>

unitree_z1_dual_arm_stackbox_v2/case4/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "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",
+    "psnr": 25.49270910031428
+}

unitree_z1_stackbox/case1/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "gt_video": "unitree_z1_stackbox/case1/unitree_z1_stackbox_case1.mp4",
+    "pred_video": "unitree_z1_stackbox/case1/output/inference/5_full_fs4.mp4",
+    "psnr": 42.83913947323794
+}

unitree_z1_stackbox/case2/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "gt_video": "unitree_z1_stackbox/case2/unitree_z1_stackbox_case2.mp4",
+    "pred_video": "unitree_z1_stackbox/case2/output/inference/15_full_fs4.mp4",
+    "psnr": 48.64571989587276
+}

unitree_z1_stackbox/case3/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "gt_video": "unitree_z1_stackbox/case3/unitree_z1_stackbox_case3.mp4",
+    "pred_video": "unitree_z1_stackbox/case3/output/inference/25_full_fs4.mp4",
+    "psnr": 45.127553229898034
+}

unitree_z1_stackbox/case4/psnr_result.json

@@ -0,0 +1,5 @@
+{
+    "gt_video": "unitree_z1_stackbox/case4/unitree_z1_stackbox_case4.mp4",
+    "pred_video": "unitree_z1_stackbox/case4/output/inference/35_full_fs4.mp4",
+    "psnr": 50.642542240144444
+}