114e09f570
rm EpisodeSampler from viz ( #389 )
2024-08-30 10:53:55 +02:00
04a995e7d1
Fix safe_action ( #395 )
2024-08-30 10:36:05 +02:00
4806336816
Add the possibility to visualize language instructions in visualize_dataset_html.py ( #388 )
...
Co-authored-by: Mishig <dmishig@gmail.com>
2024-08-28 11:50:31 +02:00
1ce418e4a1
Add koch bimanual ( #385 )
2024-08-28 00:53:31 +02:00
eb4c505cff
Support for converting OpenX datasets from RLDS format to LeRobotDataset ( #354 )
...
Signed-off-by: youliangtan <tan_you_liang@hotmail.com>
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
Co-authored-by: youliangtan <tan_you_liang@hotmail.com>
Co-authored-by: Remi <re.cadene@gmail.com>
2024-08-27 09:07:00 +02:00
aad59e6b6b
Fix videos in visualize_dataset are not in sync ( #382 )
2024-08-26 17:38:48 +02:00
9ce98bb93c
Add safety limits on relative action target ( #373 )
2024-08-26 14:30:18 +01:00
97086cdcdf
Make gripper_open_degree a config param ( #379 )
2024-08-26 12:28:16 +01:00
9c7649f140
Make sure `init_hydra_config` does not require any keys ( #376 )
2024-08-23 12:27:08 +01:00
a2592a5563
Provide more information to the user ( #358 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
Co-authored-by: Remi <re.cadene@gmail.com>
2024-08-23 11:00:35 +01:00
86bbd16d43
Improve discoverability on the hub ( #325 )
...
Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-08-19 15:16:46 +02:00
0f6e0f6d74
Fix input dim ( #365 )
2024-08-19 11:42:32 +01:00
b98ea415c1
Add dataset cards ( #363 )
2024-08-16 10:08:44 +02:00
bbe9057225
Improve control robot ; Add process to configure motor indices ( #326 )
...
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
Co-authored-by: jess-moss <jess.moss@dextrousrobotics.com>
Co-authored-by: Marina Barannikov <marina.barannikov@huggingface.co>
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-08-15 18:11:33 +02:00
2252b42337
Add visualize_dataset_html with `http.server` ( #188 )
2024-08-08 20:19:06 +03:00
7a3cb1ad34
Adjust the timestamps' description in Diffusion Policy ( #343 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-07-26 12:47:03 +01:00
f8a6574698
Add online training with TD-MPC as proof of concept ( #338 )
2024-07-25 11:16:38 +01:00
abbb1d2367
Make sure policies don't mutate the batch ( #323 )
2024-07-22 20:38:33 +01:00
0b21210d72
Convert datasets to av1 encoding ( #302 )
2024-07-22 20:08:59 +02:00
461d5472d3
Fix visualize_image_transforms ( #333 )
2024-07-18 22:26:00 +02:00
8865e19c12
Fix datasets missing versions ( #318 )
2024-07-16 23:02:31 +02:00
5f5efe7cb9
Improve error message when attempting to overwrite a training output folder ( #322 )
2024-07-16 16:50:31 +01:00
c0101f0948
Fix ACT temporal ensembling ( #319 )
2024-07-16 10:27:21 +01:00
5e54e39795
Add real robot devices and scripts to control real robot ( #288 )
...
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
2024-07-15 17:43:10 +02:00
5ffcb48a9a
Add available list of raw repo ids ( #312 )
2024-07-13 11:30:50 +02:00
471eab3d7e
Make ACT compatible with "observation.environment_state" ( #314 )
2024-07-11 13:12:22 +01:00
64425d5e00
Bug fix: fix error when setting select_target_actions_indices in vqbet ( #310 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-07-10 17:56:11 +01:00
e410e5d711
Improve video benchmark ( #282 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
Co-authored-by: Remi <re.cadene@gmail.com>
2024-07-09 20:20:25 +02:00
cc2f6e7404
Train diffusion pusht_keypoints ( #307 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-07-09 12:35:50 +01:00
a4d77b99f0
Include `observation.environment_state` with keypoints in PushT dataset ( #303 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-07-09 08:27:40 +01:00
7bd5ab16d1
Fix generation of dataset test artifact ( #306 )
2024-07-05 11:02:26 +01:00
74362ac453
Add VQ-BeT copyrights ( #299 )
2024-07-04 13:02:31 +02:00
964f9e86d6
Cleanup config defaults ( #300 )
2024-07-04 11:53:29 +02:00
342f429f1c
Add test to make sure policy dataclass configs match yaml configs ( #292 )
2024-06-26 09:09:40 +01:00
7d1542cae1
Add VQ-BeT ( #166 )
2024-06-26 08:55:02 +01:00
9aa4cdb976
Checkpoint on final step of training even when it doesn't coincide with `save_freq`. ( #284 )
2024-06-20 08:27:01 +01:00
2abef3bef9
Enable `video_reader` backend ( #220 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-06-19 17:15:25 +02:00
48951662f2
Bug fix: missing attention mask in VAE encoder in ACT policy ( #279 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-06-19 12:07:21 +01:00
11f1cb5dc9
Bug fix: fix setting different learning rates between backbone and main model in ACT policy ( #280 )
2024-06-18 13:31:35 +01:00
b72d574891
fix Unet global_cond_dim to use state dim, not action dim ( #278 )
2024-06-17 15:17:28 +01:00
15dd682714
Add multi-image support to diffusion policy ( #218 )
2024-06-17 08:11:20 +01:00
e28fa2344c
added visualization for min and max transforms ( #271 )
...
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
2024-06-17 09:09:57 +02:00
125bd93e29
Improve `push_dataset_to_hub` API + Add unit tests ( #231 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-06-13 15:18:02 +02:00
c38f535c9f
FIx make_dataset to match transforms config ( #264 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-06-12 19:45:42 +02:00
ff8f6aa6cd
Add data augmentation in LeRobotDataset ( #234 )
...
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
Co-authored-by: Remi Cadene <re.cadene@gmail.com>
2024-06-11 19:20:55 +02:00
54c9776bde
Improves Type Annotations ( #252 )
2024-06-10 19:09:48 +01:00
055a6f60c6
add root argument to the dataset visualizer to visualize local datasets ( #249 )
2024-06-10 10:44:32 +02:00
e54d6ea1eb
Make `display_sys_info.py` install-agnostic ( #253 )
2024-06-07 15:02:17 +02:00
1eb4bfe2e4
Fix videos_dir documentation ( #247 )
2024-06-05 08:25:20 +01:00
21f222fa1d
Add out_dir option to eval ( #244 )
2024-06-04 21:01:53 +02:00
33362dbd17
Adding parameter dataloading_s to console logs and wandb for tracking… ( #243 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-06-04 17:02:05 +01:00
b0d954c6e1
Fix bug in normalize to avoid divide by zero ( #239 )
...
Co-authored-by: rj <rj@teleopstrio-razer.lan>
Co-authored-by: Remi <re.cadene@gmail.com>
2024-06-04 12:21:28 +02:00
bd3111f28b
Fix `visualize_dataset.py --help` ( #241 )
2024-06-03 16:35:16 +02:00
cf15cba5fc
Remove redundant slicing operation in Diffusion Policy ( #240 )
2024-06-03 13:04:24 +01:00
d585c73f9f
Add real-world support for ACT on Aloha/Aloha2 ( #228 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-05-31 15:31:02 +02:00
504d2aaf48
add EpisodeAwareSampler ( #217 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-05-31 13:43:47 +01:00
83f4f7f7e8
Add precision param to format_big_number ( #232 )
2024-05-31 10:19:01 +02:00
633115d861
Fix chaining in MultiLerobotDataset ( #233 )
2024-05-31 09:03:28 +01:00
57fb5fe8a6
Improve documentation on VAE encoder inputs ( #215 )
2024-05-30 19:16:44 +02:00
111cd58f8a
Add `MultiLerobotDataset` for training with multiple `LeRobotDataset`s ( #229 )
2024-05-30 16:12:21 +01:00
265b0ec44d
Refactor env to add key word arguments from config yaml ( #223 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-05-30 13:45:22 +02:00
2c2e4e14ed
Add `aloha_dora_format.py` ( #201 )
...
Co-authored-by: Thomas Wolf <thomwolf@users.noreply.github.com>
2024-05-30 11:26:39 +02:00
3d625ae6d3
Handle `crop_shape=None` in Diffusion Policy ( #219 )
2024-05-28 18:27:33 +01:00
e3b9f1c19b
Add resume training ( #205 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-05-28 12:04:23 +01:00
3b86050ab0
throw an error if config.do_maks_loss and action_is_pad not provided in batch ( #213 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-05-27 09:06:26 +01:00
b6c216b590
Add Automatic Mixed Precision option for training and evaluation. ( #199 )
2024-05-20 18:57:54 +01:00
2b270d085b
Disable online training ( #202 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-05-20 18:27:54 +01:00
c4da689171
Hot fix to compute validation loss example test ( #200 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-05-20 18:30:11 +02:00
9b62c25f6c
Adds split_by_episodes to LeRobotDataset ( #158 )
2024-05-20 14:04:04 +02:00
01eae09ba6
Fix aloha real-world datasets ( #175 )
2024-05-20 13:48:09 +02:00
096149b118
Disable wandb by default ( #195 )
2024-05-17 18:01:39 +01:00
5ec0af62c6
Explain why n_encoder_layers=1 ( #193 )
2024-05-17 15:05:40 +01:00
625f0557ef
Act temporal ensembling ( #186 )
2024-05-17 14:57:49 +01:00
4d7d41cdee
Fix act action queue ( #185 )
2024-05-16 15:43:25 +01:00
c9069df9f1
Port SpatialSoftmax and remove Robomimic dependency ( #182 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-05-16 15:34:10 +01:00
68c1b13406
Make policies compatible with other/multiple image keys ( #149 )
2024-05-16 13:51:53 +01:00
f52f4f2cd2
Add copyrights ( #157 )
2024-05-15 12:13:09 +02:00
fc5cf3d84a
Fixes issue #152 - error with creating wandb artifact ( #172 )
...
Co-authored-by: Ashis Ghosh <ahsisghosh@live.com>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-05-12 08:13:12 +02:00
ced3de4c94
Fix hanging in visualize_dataset.py when num_workers > 0 ( #165 )
2024-05-11 19:28:22 +03:00
1249aee3ac
Enable logging all the information returned by the `forward` methods of policies ( #151 )
2024-05-10 07:45:32 +01:00
b187942db4
Add context manager for seeding ( #164 )
2024-05-09 17:58:39 +01:00
473345fdf6
Fix stats override in ACT config ( #161 )
2024-05-09 15:16:47 +01:00
e89521dfa0
Enable tests for TD-MPC ( #160 )
2024-05-09 13:42:12 +01:00
0ea7a8b2a3
refactor: update configuration_tdmpc.py ( #153 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-05-08 18:13:51 +01:00
460df2ccea
Support for DDIMScheduler in Diffusion Policy ( #146 )
2024-05-08 18:05:16 +01:00
f5de57b385
Fix SpatialSoftmax input shape ( #150 )
2024-05-08 14:57:29 +01:00
47de07658c
Override pretrained model config ( #147 )
2024-05-08 12:56:21 +01:00
26d9a070d8
Add policy and dataset tags to WandB logging ( #144 )
2024-05-07 09:09:21 +01:00
a8e245fb31
Remove loss masking from diffusion policy ( #135 )
2024-05-06 07:27:01 +01:00
f5e76393eb
Release cleanup ( #132 )
...
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
Co-authored-by: Cadene <re.cadene@gmail.com>
2024-05-06 03:03:14 +02:00
6eaffbef1d
Add 25 real world datasets (static + mobile aloha) ( #133 )
2024-05-05 19:13:11 +02:00
6e6feae09e
Remove additional frame from eval render ( #137 )
2024-05-05 13:49:53 +02:00
f6fe162432
Rename Diffusion Policy model repository ( #136 )
2024-05-05 12:06:58 +01:00
f3bba0270d
Remove EMA model from Diffusion Policy ( #134 )
2024-05-05 11:26:12 +01:00
d747195c57
Fix loops in eval.py ( #128 )
2024-05-04 15:21:10 +01:00
c77633c38c
Add regression tests ( #119 )
...
- Add `tests/scripts/save_policy_to_safetensor.py` to generate test artifacts
- Add `test_backward_compatibility to test generated outputs from the policies against artifacts
2024-05-04 16:20:30 +02:00
19812ca470
Add dataset visualization with rerun.io ( #131 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-05-04 16:07:14 +02:00
c015252e20
Remove batch length restrictions in select_action ( #123 )
2024-05-04 15:33:55 +02:00
bccee745c3
Refactor eval.py ( #127 )
2024-05-03 17:33:16 +01:00
b2cda12f87
Add video decoding to LeRobotDataset ( #92 )
2024-05-03 00:50:19 +02:00
c1668924ab
Fix missing `policy.to(device)` in policy factory ( #126 )
2024-05-01 17:26:58 +01:00
d1855a202a
Refactor TD-MPC ( #103 )
...
Co-authored-by: Cadene <re.cadene@gmail.com>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-05-01 16:40:04 +01:00
a4891095e4
Use PytorchModelHubMixin to save models as safetensors ( #125 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-05-01 16:17:18 +01:00
01d5490d44
Follow `transformers` single file naming conventions ( #124 )
2024-05-01 13:09:42 +01:00
986583dc5c
Nest ACT model in ACT Policy ( #122 )
2024-04-30 17:17:40 +01:00
9d60dce6f3
Tidy up yaml configs ( #121 )
2024-04-30 16:08:59 +01:00
e4e739f4f8
Refactor push_dataset_to_hub ( #118 )
2024-04-30 14:25:41 +02:00
2765877f28
Speed up CI, add more checks ( #115 )
...
- Split pytest and end-to-end tests into separate jobs
- Add poetry check to ensure pyproject.toml and poetry.lock are in sync
- Add ruff format --diff to ensure style formatting is applied (fails if ruff would reformat anything)
2024-04-29 23:05:55 +02:00
1ec5f77f7c
Remove mask check key in XarmProcessor ( #117 )
2024-04-29 22:00:37 +02:00
508bd92d03
Remove `update` method from the policy ( #99 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-29 12:27:58 +02:00
5b4fd8891d
Update UmiProcessor default fps to 10 ( #116 )
2024-04-29 12:11:34 +02:00
ccffa9e406
Fix policy defaults ( #113 )
2024-04-29 08:26:59 +01:00
791506dfb8
Remove warnings ( #111 )
...
- Replace `use_pretrained_backbone` with `pretrained_backbone_weights`
- Bump diffusers' minimum version `0.26.3` -> `0.27.2`
- Add ignore flags in CI's pytest
- Change Box observation spaces in simulation environments
- Set `version_base="1.2"` in Hydra initializations
- Bump einops' minimum version `0.7.0` -> `0.8.0`
2024-04-29 00:31:33 +02:00
55dc9f7f51
Refactor the download and publication of the datasets and convert it into CLI script ( #95 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-04-29 00:08:17 +02:00
81e490d46f
Add UMI-gripper dataset ( #83 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-04-28 18:41:07 +02:00
45f351c618
Make sure targets are normalized too ( #106 )
2024-04-26 11:18:39 +01:00
659c69a1c0
Refactor datasets into LeRobotDataset ( #91 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-25 12:23:12 +02:00
e760e4cd63
Move normalization to policy for act and diffusion ( #90 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-25 11:47:38 +02:00
c1bcf857c5
Fix online training ( #94 )
2024-04-23 18:54:55 +02:00
1030ea0070
Loads episode_data_index and stats during dataset __init__ ( #85 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-23 14:13:25 +02:00
e2168163cd
Quality of life patches for eval.py ( #86 )
2024-04-19 12:33:47 +01:00
8d980940a2
Fix tolerance for delta_timestamps ( #84 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-04-18 18:48:22 +01:00
7ad1909641
Tests cleaning & simplification ( #81 )
2024-04-18 14:47:42 +02:00
0928afd37d
Improve dataset examples ( #82 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-18 11:43:16 +02:00
dd9c6eed15
Add temporary patch in TD-MPC
2024-04-17 16:27:57 +01:00
2298ddf226
wip
2024-04-17 16:21:37 +01:00
63e5ec6483
revert some formatting changes
2024-04-17 11:40:49 +01:00
c50a13ab31
draft
2024-04-17 10:50:54 +01:00
296bbfe1ad
Merge branch 'fix_stats_saving' into unify_policy_api
2024-04-17 09:08:04 +01:00
c9454333d8
revision
2024-04-17 09:02:35 +01:00
1331d3b4e4
fix issue with saving freshly computed stats
2024-04-17 08:49:28 +01:00
bff4b673c9
Merge remote-tracking branch 'upstream/main' into unify_policy_api
2024-04-17 08:08:57 +01:00
3f1c322d56
Merge pull request #73 from huggingface/user/rcadene/2024_04_14_hf_datasets
...
Use Hugging Face datasets.Dataset
2024-04-16 21:54:37 +02:00
fbc31d906c
Merge pull request #74 from huggingface/user/aliberts/2024_04_15_setup_contributions
...
Setup contributions
2024-04-16 19:51:13 +02:00
91badebdfc
fix tests
2024-04-16 17:29:31 +00:00
4327e43f19
fix merge thingy
2024-04-16 17:24:25 +00:00
36d9e885ef
Address comments
2024-04-16 17:20:54 +00:00
b241ea46dd
move download_and_upload_dataset.py to root_dir
2024-04-16 17:20:53 +00:00
e09d25267e
fix online training
2024-04-16 17:20:53 +00:00
4a3eac4743
fix unit tests, stats was missing, visualize_dataset was broken
2024-04-16 17:20:53 +00:00
0980fff6cc
HF datasets works
2024-04-16 17:19:40 +00:00
5edd9a89a0
Move stats_dataset init into else statement -> faster init
2024-04-16 17:19:39 +00:00
c7a8218620
typo
2024-04-16 17:19:39 +00:00
67d79732f9
Add download_and_upload_dataset.py in script, update all datasets, update online training
2024-04-16 17:19:39 +00:00
c6aca7fe44
For Pusht: use hf datasets to train, rename load_data_with_delta_timestamps -> load_previous_and_future_frames
2024-04-16 17:19:06 +00:00
cb3978b5f3
backup wip
2024-04-16 18:12:39 +01:00
0eb899de73
Merge remote-tracking branch 'upstream/main' into unify_policy_api
2024-04-16 17:30:41 +01:00
a9496fde39
revision 1
2024-04-16 17:15:51 +01:00
23be5e1e7b
backup wip
2024-04-16 16:31:44 +01:00
9c2f10bd04
ready for review
2024-04-16 13:43:58 +01:00
Mishig
Simon Alibert
Michel Aractingi
Remi
Alexander Soare
Zhuoheng Li
NielsRogge
Remi
Halvard Bariller
Seungjae Lee
Thomas Wolf
Jihoon Oh
Marina Barannikov
Wael Karkoub
Thomas Lips
amandip7
Ruijie
Radek Osmulski
Akshay Kashyap
AshisGhosh
Ikko Eltociear Ashimine
Adil Zouitine
Quentin Gallouédec