solarian-diffusion 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (159) hide show
  1. diffusion_policy/__init__.py +0 -0
  2. diffusion_policy/codecs/__init__.py +0 -0
  3. diffusion_policy/codecs/imagecodecs_numcodecs.py +1408 -0
  4. diffusion_policy/common/__init__.py +0 -0
  5. diffusion_policy/common/checkpoint_util.py +64 -0
  6. diffusion_policy/common/json_logger.py +117 -0
  7. diffusion_policy/common/normalize_util.py +251 -0
  8. diffusion_policy/common/pose_repr_util.py +112 -0
  9. diffusion_policy/common/pytorch_util.py +82 -0
  10. diffusion_policy/common/q_critic_util.py +135 -0
  11. diffusion_policy/common/replay_buffer.py +672 -0
  12. diffusion_policy/common/sampler.py +204 -0
  13. diffusion_policy/config/legacy/task/blockpush_lowdim_seed.yaml +34 -0
  14. diffusion_policy/config/legacy/task/blockpush_lowdim_seed_abs.yaml +34 -0
  15. diffusion_policy/config/legacy/task/can_image.yaml +64 -0
  16. diffusion_policy/config/legacy/task/can_image_abs.yaml +64 -0
  17. diffusion_policy/config/legacy/task/can_lowdim.yaml +45 -0
  18. diffusion_policy/config/legacy/task/can_lowdim_abs.yaml +46 -0
  19. diffusion_policy/config/legacy/task/kitchen_lowdim.yaml +33 -0
  20. diffusion_policy/config/legacy/task/kitchen_lowdim_abs.yaml +38 -0
  21. diffusion_policy/config/legacy/task/lift_abs.yaml +72 -0
  22. diffusion_policy/config/legacy/task/lift_image.yaml +64 -0
  23. diffusion_policy/config/legacy/task/lift_image_abs.yaml +63 -0
  24. diffusion_policy/config/legacy/task/lift_lowdim.yaml +46 -0
  25. diffusion_policy/config/legacy/task/lift_lowdim_abs.yaml +47 -0
  26. diffusion_policy/config/legacy/task/pusht_image.yaml +40 -0
  27. diffusion_policy/config/legacy/task/pusht_lowdim.yaml +34 -0
  28. diffusion_policy/config/legacy/task/real_pusht_image.yaml +47 -0
  29. diffusion_policy/config/legacy/task/square_abs.yaml +72 -0
  30. diffusion_policy/config/legacy/task/square_image.yaml +64 -0
  31. diffusion_policy/config/legacy/task/square_image_abs.yaml +64 -0
  32. diffusion_policy/config/legacy/task/square_lowdim.yaml +46 -0
  33. diffusion_policy/config/legacy/task/square_lowdim_abs.yaml +47 -0
  34. diffusion_policy/config/legacy/task/tool_hang_abs.yaml +71 -0
  35. diffusion_policy/config/legacy/task/tool_hang_image.yaml +63 -0
  36. diffusion_policy/config/legacy/task/tool_hang_image_abs.yaml +63 -0
  37. diffusion_policy/config/legacy/task/tool_hang_lowdim.yaml +45 -0
  38. diffusion_policy/config/legacy/task/tool_hang_lowdim_abs.yaml +46 -0
  39. diffusion_policy/config/legacy/task/transport_image.yaml +75 -0
  40. diffusion_policy/config/legacy/task/transport_image_abs.yaml +75 -0
  41. diffusion_policy/config/legacy/task/transport_lowdim.yaml +49 -0
  42. diffusion_policy/config/legacy/task/transport_lowdim_abs.yaml +49 -0
  43. diffusion_policy/config/legacy/task/umi.yaml +45 -0
  44. diffusion_policy/config/legacy/task/umi_image.yaml +36 -0
  45. diffusion_policy/config/legacy/task/umi_teleop_image.yaml +41 -0
  46. diffusion_policy/config/legacy/train_bet_lowdim_workspace.yaml +132 -0
  47. diffusion_policy/config/legacy/train_diffusion_transformer_hybrid_workspace.yaml +141 -0
  48. diffusion_policy/config/legacy/train_diffusion_transformer_lowdim_kitchen_workspace.yaml +146 -0
  49. diffusion_policy/config/legacy/train_diffusion_transformer_lowdim_pusht_workspace.yaml +146 -0
  50. diffusion_policy/config/legacy/train_diffusion_transformer_lowdim_workspace.yaml +146 -0
  51. diffusion_policy/config/legacy/train_diffusion_transformer_real_hybrid_workspace.yaml +144 -0
  52. diffusion_policy/config/legacy/train_diffusion_transformer_umi_teleop_hybrid_workspace.yaml +156 -0
  53. diffusion_policy/config/legacy/train_diffusion_unet_ddim_hybrid_workspace.yaml +140 -0
  54. diffusion_policy/config/legacy/train_diffusion_unet_ddim_lowdim_workspace.yaml +146 -0
  55. diffusion_policy/config/legacy/train_diffusion_unet_hybrid_workspace.yaml +137 -0
  56. diffusion_policy/config/legacy/train_diffusion_unet_image_pretrained_workspace.yaml +149 -0
  57. diffusion_policy/config/legacy/train_diffusion_unet_image_workspace.yaml +150 -0
  58. diffusion_policy/config/legacy/train_diffusion_unet_lowdim_workspace.yaml +143 -0
  59. diffusion_policy/config/legacy/train_diffusion_unet_real_hybrid_workspace.yaml +141 -0
  60. diffusion_policy/config/legacy/train_diffusion_unet_real_image_workspace.yaml +152 -0
  61. diffusion_policy/config/legacy/train_diffusion_unet_real_pretrained_workspace.yaml +152 -0
  62. diffusion_policy/config/legacy/train_diffusion_unet_timm_workspace.yaml +145 -0
  63. diffusion_policy/config/legacy/train_diffusion_unet_umi_hybrid_workspace.yaml +141 -0
  64. diffusion_policy/config/legacy/train_diffusion_unet_umi_teleop_hybrid_workspace.yaml +153 -0
  65. diffusion_policy/config/legacy/train_diffusion_unet_umi_timm_workspace.yaml +145 -0
  66. diffusion_policy/config/legacy/train_diffusion_unet_umi_workspace.yaml +150 -0
  67. diffusion_policy/config/legacy/train_diffusion_unet_video_workspace.yaml +128 -0
  68. diffusion_policy/config/legacy/train_ibc_dfo_hybrid_workspace.yaml +111 -0
  69. diffusion_policy/config/legacy/train_ibc_dfo_lowdim_workspace.yaml +109 -0
  70. diffusion_policy/config/legacy/train_ibc_dfo_real_hybrid_workspace.yaml +111 -0
  71. diffusion_policy/config/legacy/train_robomimic_image_workspace.yaml +92 -0
  72. diffusion_policy/config/legacy/train_robomimic_lowdim_workspace.yaml +92 -0
  73. diffusion_policy/config/legacy/train_robomimic_real_image_workspace.yaml +92 -0
  74. diffusion_policy/config/rl_annotate.yaml +265 -0
  75. diffusion_policy/config/rl_annotate_per_frame.yaml +162 -0
  76. diffusion_policy/config/rl_annotate_per_frame_v4.yaml +162 -0
  77. diffusion_policy/config/rl_annotate_v2.yaml +141 -0
  78. diffusion_policy/config/rl_annotate_v3.yaml +165 -0
  79. diffusion_policy/config/task/lift.yaml +89 -0
  80. diffusion_policy/config/task/square.yaml +92 -0
  81. diffusion_policy/config/task/tool_hang.yaml +93 -0
  82. diffusion_policy/config/task/tool_hang_abs.yaml +71 -0
  83. diffusion_policy/config/task/umi.yaml +105 -0
  84. diffusion_policy/config/task/umi_bimanual.yaml +135 -0
  85. diffusion_policy/config/task/umi_cup_wild.yaml +106 -0
  86. diffusion_policy/config/task/umi_image.yaml +36 -0
  87. diffusion_policy/config/task/umi_pick_lego.yaml +106 -0
  88. diffusion_policy/config/task/umi_pick_single_lego_175.yaml +106 -0
  89. diffusion_policy/config/task/umi_pick_single_lego_bbox.yaml +135 -0
  90. diffusion_policy/config/task/umi_teleop_image.yaml +41 -0
  91. diffusion_policy/config/train_diffusion_transformer_umi_bimanual_workspace.yaml +185 -0
  92. diffusion_policy/config/train_diffusion_transformer_umi_workspace.yaml +185 -0
  93. diffusion_policy/config/train_diffusion_unet_image_workspace.yaml +152 -0
  94. diffusion_policy/config/train_diffusion_unet_timm_robomimic_workspace.yaml +152 -0
  95. diffusion_policy/config/train_diffusion_unet_timm_umi_cup_wild.yaml +260 -0
  96. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_lego_pile_bbox.yaml +265 -0
  97. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_lego_pile_bbox_awr.yaml +324 -0
  98. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_lego_pile_bbox_parl.yaml +399 -0
  99. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_single_lego.yaml +258 -0
  100. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_single_lego_125.yaml +260 -0
  101. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_single_lego_175.yaml +260 -0
  102. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_single_lego_bbox.yaml +265 -0
  103. diffusion_policy/config/train_diffusion_unet_timm_umi_pick_two_legos_bbox.yaml +265 -0
  104. diffusion_policy/config/train_diffusion_unet_timm_umi_workspace.yaml +224 -0
  105. diffusion_policy/config/train_diffusion_unet_timm_umi_workspace_lego.yaml +213 -0
  106. diffusion_policy/config/train_diffusion_unet_timm_umi_workspace_lego_resume.yaml +213 -0
  107. diffusion_policy/config/train_diffusion_unet_timm_umi_workspace_pick_lego.yaml +254 -0
  108. diffusion_policy/config/train_diffusion_unet_timm_umi_workspace_red_cup.yaml +219 -0
  109. diffusion_policy/config/train_diffusion_unet_umi_bimanual_workspace.yaml +203 -0
  110. diffusion_policy/config/train_iql_umi.yaml +186 -0
  111. diffusion_policy/config/train_iql_umi_v2.yaml +212 -0
  112. diffusion_policy/config/train_iql_umi_v3.yaml +212 -0
  113. diffusion_policy/dataset/__init__.py +0 -0
  114. diffusion_policy/dataset/base_dataset.py +76 -0
  115. diffusion_policy/dataset/umi_dataset.py +652 -0
  116. diffusion_policy/env_runner/__init__.py +0 -0
  117. diffusion_policy/env_runner/base_image_runner.py +9 -0
  118. diffusion_policy/env_runner/real_pusht_image_runner.py +10 -0
  119. diffusion_policy/model/__init__.py +0 -0
  120. diffusion_policy/model/common/__init__.py +0 -0
  121. diffusion_policy/model/common/dict_of_tensor_mixin.py +38 -0
  122. diffusion_policy/model/common/lr_scheduler.py +46 -0
  123. diffusion_policy/model/common/module_attr_mixin.py +14 -0
  124. diffusion_policy/model/common/normalizer.py +353 -0
  125. diffusion_policy/model/common/tensor_util.py +960 -0
  126. diffusion_policy/model/diffusion/__init__.py +0 -0
  127. diffusion_policy/model/diffusion/conditional_unet1d.py +238 -0
  128. diffusion_policy/model/diffusion/conv1d_components.py +46 -0
  129. diffusion_policy/model/diffusion/ema_model.py +88 -0
  130. diffusion_policy/model/diffusion/mask_generator.py +221 -0
  131. diffusion_policy/model/diffusion/positional_embedding.py +17 -0
  132. diffusion_policy/model/vision/__init__.py +0 -0
  133. diffusion_policy/model/vision/crop_randomizer.py +288 -0
  134. diffusion_policy/model/vision/multi_image_obs_encoder.py +195 -0
  135. diffusion_policy/model/vision/timm_obs_encoder.py +525 -0
  136. diffusion_policy/policy/__init__.py +0 -0
  137. diffusion_policy/policy/base_image_policy.py +27 -0
  138. diffusion_policy/policy/diffusion_unet_image_policy.py +264 -0
  139. diffusion_policy/policy/diffusion_unet_timm_policy.py +607 -0
  140. diffusion_policy/policy/parl_action_optimizer.py +675 -0
  141. diffusion_policy/workspace/__init__.py +0 -0
  142. diffusion_policy/workspace/base_workspace.py +146 -0
  143. diffusion_policy/workspace/train_diffusion_unet_image_workspace.py +1585 -0
  144. solarian_diffusion/__init__.py +32 -0
  145. solarian_diffusion/config.py +31 -0
  146. solarian_diffusion/policy_server.py +316 -0
  147. solarian_diffusion/rtc.py +272 -0
  148. solarian_diffusion/service.py +16 -0
  149. solarian_diffusion/trainer.py +213 -0
  150. solarian_diffusion-0.1.0.dist-info/METADATA +126 -0
  151. solarian_diffusion-0.1.0.dist-info/RECORD +159 -0
  152. solarian_diffusion-0.1.0.dist-info/WHEEL +5 -0
  153. solarian_diffusion-0.1.0.dist-info/entry_points.txt +8 -0
  154. solarian_diffusion-0.1.0.dist-info/licenses/LICENSE +201 -0
  155. solarian_diffusion-0.1.0.dist-info/licenses/NOTICE +45 -0
  156. solarian_diffusion-0.1.0.dist-info/top_level.txt +3 -0
  157. umi/__init__.py +0 -0
  158. umi/common/__init__.py +0 -0
  159. umi/common/pose_util.py +115 -0
@@ -0,0 +1,135 @@
1
+ """Load a trained IQL critic checkpoint into a runnable ``nn.Module``.
2
+
3
+ This is the single source of truth for "open the .ckpt produced by
4
+ ``TrainIqlWorkspace`` and return a ready-to-use ``IQLCritic`` on the
5
+ target device". Three call sites delegate to it:
6
+
7
+ * ``policy_server.load_q_critic`` (online inference: rerank /
8
+ Q-guidance during eval)
9
+ * ``zarr_q_v._load_iql_workspace`` (offline Q/V materialization
10
+ that writes ``rl/q`` / ``rl/v`` back into the dataset zarr)
11
+ * PA-RL training in
12
+ ``TrainDiffusionUnetImageWorkspace`` (relabel pass that produces
13
+ optimized action chunks for the diffusion DDPM target)
14
+
15
+ Keeping the load logic in one place is what guarantees that a Q value
16
+ seen during PA-RL relabel matches the Q value the policy server
17
+ observes at deployment time -- otherwise it would be very easy for a
18
+ subtle env / cfg-override drift to introduce a calibration gap that's
19
+ invisible until the policy actively learns to exploit it.
20
+ """
21
+
22
+ from __future__ import annotations
23
+
24
+ import logging as _logging
25
+ import os
26
+ import time
27
+ from typing import Any, Optional, Tuple
28
+
29
+ import dill
30
+ import hydra
31
+ import torch
32
+ from omegaconf import OmegaConf, open_dict
33
+
34
+ # IQL workspace registers an ``${eval:...}`` resolver via its module
35
+ # import. Mirror it here in case this util is loaded BEFORE any IQL
36
+ # code path -- otherwise OmegaConf.select on a saved cfg blows up.
37
+ OmegaConf.register_new_resolver("eval", eval, replace=True)
38
+
39
+ _default_logger = _logging.getLogger(__name__)
40
+
41
+
42
+ def load_iql_critic(
43
+ ckpt_path: str,
44
+ device: torch.device,
45
+ *,
46
+ logger: Optional[_logging.Logger] = None,
47
+ ) -> Tuple[torch.nn.Module, Any]:
48
+ """Load an IQL critic checkpoint and return ``(critic.eval().to(device), cfg)``.
49
+
50
+ Behavior matches the previous in-line implementations in
51
+ ``zarr_q_v._load_iql_workspace`` and ``policy_server.load_q_critic``
52
+ (which now delegate to this):
53
+
54
+ * Reads the pickle with ``dill`` (the same pickler
55
+ ``BaseWorkspace.save_checkpoint`` uses) onto CPU.
56
+ * Forces ``iql.pretrained_obs_encoder_ckpt = None`` because the
57
+ path was baked at training time (typically under ``/data/...``
58
+ on the Modal volume) and likely does not exist locally. The
59
+ following ``state_dict`` load restores the encoder weights
60
+ anyway, so this is purely a "skip a download we don't need".
61
+ * Leaves ``policy.obs_encoder.pretrained=True``: ``TimmObsEncoder``
62
+ asserts ``frozen=True => pretrained=True`` and IQL defaults to
63
+ ``freeze_visual=true``. The trained ``state_dict`` overwrites
64
+ the timm weights a moment later, so this is at most a one-time
65
+ HF-cache read.
66
+ * Loads ``state_dicts['model']`` with ``strict=False`` and warns
67
+ on missing / unexpected keys. A truly garbled ckpt should still
68
+ fail downstream when ``q_values`` produces nonsense.
69
+ * Calls ``.eval().to(device)`` on the critic. Callers can add a
70
+ ``torch.cuda.synchronize()`` afterward if they care about
71
+ accurate timing.
72
+
73
+ Args:
74
+ ckpt_path: path to the IQL ``.ckpt``. ``~`` is expanded.
75
+ device: target device for the critic.
76
+ logger: optional logger; defaults to a module-local logger so
77
+ this util is silent under ``pytest`` / scripts that haven't
78
+ configured logging.
79
+
80
+ Returns:
81
+ ``(critic, cfg)`` -- ``critic`` is the loaded ``IQLCritic``
82
+ in ``eval()`` mode on ``device``; ``cfg`` is the full Hydra
83
+ cfg snapshot the ckpt was trained with (callers reuse it to
84
+ rebuild matching datasets / shape_meta).
85
+ """
86
+ log = logger or _default_logger
87
+ ckpt_path = os.path.expanduser(ckpt_path)
88
+ if not os.path.isfile(ckpt_path):
89
+ raise FileNotFoundError(f"IQL checkpoint not found: {ckpt_path}")
90
+
91
+ log.info(f"Loading IQL checkpoint: {ckpt_path}")
92
+ t0 = time.perf_counter()
93
+ with open(ckpt_path, "rb") as f:
94
+ payload = torch.load(f, map_location="cpu", pickle_module=dill)
95
+ log.info(f" read payload in {time.perf_counter() - t0:.2f}s")
96
+
97
+ cfg = payload["cfg"]
98
+
99
+ try:
100
+ if OmegaConf.select(cfg, "iql.pretrained_obs_encoder_ckpt"):
101
+ with open_dict(cfg):
102
+ cfg.iql.pretrained_obs_encoder_ckpt = None
103
+ except Exception as e:
104
+ log.warning(f"could not override iql.pretrained_obs_encoder_ckpt: {e}")
105
+
106
+ log.info(f" workspace target: {cfg._target_}")
107
+ cls = hydra.utils.get_class(cfg._target_)
108
+
109
+ t0 = time.perf_counter()
110
+ workspace = cls(cfg)
111
+ log.info(f" built workspace in {time.perf_counter() - t0:.2f}s")
112
+
113
+ sds = payload.get("state_dicts", {})
114
+ if "model" not in sds:
115
+ raise RuntimeError(
116
+ f"IQL checkpoint has no state_dicts['model']; "
117
+ f"got keys {list(sds.keys())}"
118
+ )
119
+
120
+ missing, unexpected = workspace.model.load_state_dict(
121
+ sds["model"], strict=False
122
+ )
123
+ if missing:
124
+ log.warning(
125
+ f" load_state_dict: {len(missing)} missing keys "
126
+ f"(first: {missing[:3]})"
127
+ )
128
+ if unexpected:
129
+ log.warning(
130
+ f" load_state_dict: {len(unexpected)} unexpected keys "
131
+ f"(first: {unexpected[:3]})"
132
+ )
133
+
134
+ model = workspace.model.eval().to(device)
135
+ return model, cfg