olivame/unifolm-world-model-action
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

实现了Context 预计算和缓存功能，提升了采样效率。 psnr不下降

Browse Source
This commit is contained in:
olivame
2026-02-09 17:42:47 +00:00
parent f192c8aca9
commit 6dca3696d8
4 changed files with 119 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
src/unifolm_wma/models/diffusion_head/conditional_unet1d.py
View File

@@ -501,6 +501,10 @@ class ConditionalUnet1D(nn.Module):
self.last_frame_only = last_frame_only
self.horizon = horizon
# Context precomputation cache
self._global_cond_cache_enabled = False
self._global_cond_cache = {}
def forward(self,
sample: torch.Tensor,
timestep: Union[torch.Tensor, float, int],
@@ -530,14 +534,20 @@ class ConditionalUnet1D(nn.Module):
B, T, D = sample.shape
if self.use_linear_act_proj:
sample = self.proj_in_action(sample.unsqueeze(-1))
global_cond = self.obs_encoder(cond)
global_cond = rearrange(global_cond,
'(b t) d -> b 1 (t d)',
b=B,
t=self.n_obs_steps)
global_cond = repeat(global_cond,
'b c d -> b (repeat c) d',
repeat=T)
_gc_key = (cond['image'].data_ptr(), cond['agent_pos'].data_ptr())
if self._global_cond_cache_enabled and _gc_key in self._global_cond_cache:
global_cond = self._global_cond_cache[_gc_key]
else:
global_cond = self.obs_encoder(cond)
global_cond = rearrange(global_cond,
'(b t) d -> b 1 (t d)',
b=B,
t=self.n_obs_steps)
global_cond = repeat(global_cond,
'b c d -> b (repeat c) d',
repeat=T)
if self._global_cond_cache_enabled:
self._global_cond_cache[_gc_key] = global_cond
else:
sample = einops.rearrange(sample, 'b h t -> b t h')
sample = self.proj_in_horizon(sample)

3
src/unifolm_wma/models/samplers/ddim.py
View File

@@ -7,6 +7,7 @@ from unifolm_wma.utils.common import noise_like
from unifolm_wma.utils.common import extract_into_tensor
from tqdm import tqdm
from unifolm_wma.modules.attention import enable_cross_attn_kv_cache, disable_cross_attn_kv_cache
from unifolm_wma.modules.networks.wma_model import enable_ctx_cache, disable_ctx_cache
class DDIMSampler(object):
@@ -245,6 +246,7 @@ class DDIMSampler(object):
dp_ddim_scheduler_state.set_timesteps(len(timesteps))
ts = torch.empty((b, ), device=device, dtype=torch.long)
enable_cross_attn_kv_cache(self.model)
enable_ctx_cache(self.model)
try:
for i, step in enumerate(iterator):
index = total_steps - i - 1
@@ -305,6 +307,7 @@ class DDIMSampler(object):
intermediates['x_inter_state'].append(state)
finally:
disable_cross_attn_kv_cache(self.model)
disable_ctx_cache(self.model)
return img, action, state, intermediates

135
src/unifolm_wma/modules/networks/wma_model.py
View File

@@ -685,6 +685,10 @@ class WMAModel(nn.Module):
self.action_token_projector = instantiate_from_config(
stem_process_config)
# Context precomputation cache
self._ctx_cache_enabled = False
self._ctx_cache = {}
def forward(self,
x: Tensor,
x_action: Tensor,
@@ -720,58 +724,64 @@ class WMAModel(nn.Module):
repeat_only=False).type(x.dtype)
emb = self.time_embed(t_emb)
bt, l_context, _ = context.shape
if self.base_model_gen_only:
assert l_context == 77 + self.n_obs_steps * 16, ">>> ERROR Context dim 1 ..." ## NOTE HANDCODE
_ctx_key = context.data_ptr()
if self._ctx_cache_enabled and _ctx_key in self._ctx_cache:
context = self._ctx_cache[_ctx_key]
else:
if l_context == self.n_obs_steps + 77 + t * 16:
context_agent_state = context[:, :self.n_obs_steps]
context_text = context[:, self.n_obs_steps:self.n_obs_steps +
77, :]
context_img = context[:, self.n_obs_steps + 77:, :]
context_agent_state = context_agent_state.repeat_interleave(
repeats=t, dim=0)
context_text = context_text.repeat_interleave(repeats=t, dim=0)
context_img = rearrange(context_img,
'b (t l) c -> (b t) l c',
t=t)
context = torch.cat(
[context_agent_state, context_text, context_img], dim=1)
elif l_context == self.n_obs_steps + 16 + 77 + t * 16:
context_agent_state = context[:, :self.n_obs_steps]
context_agent_action = context[:, self.
n_obs_steps:self.n_obs_steps +
16, :]
context_agent_action = rearrange(
context_agent_action.unsqueeze(2), 'b t l d -> (b t) l d')
context_agent_action = self.action_token_projector(
context_agent_action)
context_agent_action = rearrange(context_agent_action,
'(b o) l d -> b o l d',
o=t)
context_agent_action = rearrange(context_agent_action,
'b o (t l) d -> b o t l d',
t=t)
context_agent_action = context_agent_action.permute(
0, 2, 1, 3, 4)
context_agent_action = rearrange(context_agent_action,
'b t o l d -> (b t) (o l) d')
bt, l_context, _ = context.shape
if self.base_model_gen_only:
assert l_context == 77 + self.n_obs_steps * 16, ">>> ERROR Context dim 1 ..." ## NOTE HANDCODE
else:
if l_context == self.n_obs_steps + 77 + t * 16:
context_agent_state = context[:, :self.n_obs_steps]
context_text = context[:, self.n_obs_steps:self.n_obs_steps +
77, :]
context_img = context[:, self.n_obs_steps + 77:, :]
context_agent_state = context_agent_state.repeat_interleave(
repeats=t, dim=0)
context_text = context_text.repeat_interleave(repeats=t, dim=0)
context_img = rearrange(context_img,
'b (t l) c -> (b t) l c',
t=t)
context = torch.cat(
[context_agent_state, context_text, context_img], dim=1)
elif l_context == self.n_obs_steps + 16 + 77 + t * 16:
context_agent_state = context[:, :self.n_obs_steps]
context_agent_action = context[:, self.
n_obs_steps:self.n_obs_steps +
16, :]
context_agent_action = rearrange(
context_agent_action.unsqueeze(2), 'b t l d -> (b t) l d')
context_agent_action = self.action_token_projector(
context_agent_action)
context_agent_action = rearrange(context_agent_action,
'(b o) l d -> b o l d',
o=t)
context_agent_action = rearrange(context_agent_action,
'b o (t l) d -> b o t l d',
t=t)
context_agent_action = context_agent_action.permute(
0, 2, 1, 3, 4)
context_agent_action = rearrange(context_agent_action,
'b t o l d -> (b t) (o l) d')
context_text = context[:, self.n_obs_steps +
16:self.n_obs_steps + 16 + 77, :]
context_text = context_text.repeat_interleave(repeats=t, dim=0)
context_text = context[:, self.n_obs_steps +
16:self.n_obs_steps + 16 + 77, :]
context_text = context_text.repeat_interleave(repeats=t, dim=0)
context_img = context[:, self.n_obs_steps + 16 + 77:, :]
context_img = rearrange(context_img,
'b (t l) c -> (b t) l c',
t=t)
context_agent_state = context_agent_state.repeat_interleave(
repeats=t, dim=0)
context = torch.cat([
context_agent_state, context_agent_action, context_text,
context_img
],
dim=1)
context_img = context[:, self.n_obs_steps + 16 + 77:, :]
context_img = rearrange(context_img,
'b (t l) c -> (b t) l c',
t=t)
context_agent_state = context_agent_state.repeat_interleave(
repeats=t, dim=0)
context = torch.cat([
context_agent_state, context_agent_action, context_text,
context_img
],
dim=1)
if self._ctx_cache_enabled:
self._ctx_cache[_ctx_key] = context
emb = emb.repeat_interleave(repeats=t, dim=0)
@@ -846,3 +856,30 @@ class WMAModel(nn.Module):
s_y = torch.zeros_like(x_state)
return y, a_y, s_y
def enable_ctx_cache(model):
"""Enable context precomputation cache on WMAModel and its action/state UNets."""
for m in model.modules():
if isinstance(m, WMAModel):
m._ctx_cache_enabled = True
m._ctx_cache = {}
# conditional_unet1d cache
from unifolm_wma.models.diffusion_head.conditional_unet1d import ConditionalUnet1D
for m in model.modules():
if isinstance(m, ConditionalUnet1D):
m._global_cond_cache_enabled = True
m._global_cond_cache = {}
def disable_ctx_cache(model):
"""Disable and clear context precomputation cache."""
for m in model.modules():
if isinstance(m, WMAModel):
m._ctx_cache_enabled = False
m._ctx_cache = {}
from unifolm_wma.models.diffusion_head.conditional_unet1d import ConditionalUnet1D
for m in model.modules():
if isinstance(m, ConditionalUnet1D):
m._global_cond_cache_enabled = False
m._global_cond_cache = {}