e7abcc2ffd
add EpisodeAwareSampler
...
EpisodeAwareSampler allows the dropping of first n or last n frames
from each episode.
Additionally, you can select which episodes to run on by passig in
their ids (complements functionality of the hf dataset slice syntax
to give extra flexibility to the user).
* modify train.py and diffusion.yaml to leverage new functionality
and train on pusht with last 7 steps per episode dropped
* add unit tests
2024-05-30 07:36:58 +10:00
13310681b1
Enable cuda for end-to-end tests ( #222 )
2024-05-29 23:02:23 +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
7ec76ee235
Fix nightly builds ( #216 )
2024-05-28 10:43:34 +02:00
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
6d39b73399
Adds a tutorial section on how to use arbitrary configuration files ( #206 )
2024-05-24 12:39:11 +01:00
aca424a481
Add dev docker image ( #189 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-05-23 14:39:14 +02:00
35c1ce7a66
Fix install issues ( #191 )
2024-05-23 14:25:18 +02:00
e67da1d7a6
Add tutorials for using the training script and ( #196 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-05-21 16:47:49 +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
19dfb9144a
Update the README to reflect WandB disabled by default ( #198 )
2024-05-20 09:02:24 +01:00
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
89c6be84ca
Limit datasets major update ( #176 )
...
Co-authored-by: Quentin Lhoest <42851186+lhoestq@users.noreply.github.com>
Co-authored-by: Quentin Lhoest <lhoest.q@gmail.com>
2024-05-12 08:15:07 +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
29a196c5dd
Fix #173 - Require gym-pusht to be installed for test_examples_3_and_2 ( #174 )
2024-05-12 08:08:59 +02:00
ced3de4c94
Fix hanging in visualize_dataset.py when num_workers > 0 ( #165 )
2024-05-11 19:28:22 +03:00
7b47ab211b
Remove torchrl acknowledgement ( #177 )
2024-05-11 14:45:51 +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
7bb5b15f4c
Remove dependencies upper bounds constraints ( #145 )
2024-05-08 17:23:10 +00:00
df914aa76c
Update dev docker build ( #148 )
2024-05-08 17:21:58 +00:00
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
eb6bfe01b2
Relax version contraints & poetry lock ( #139 )
2024-05-06 17:38:29 +02:00
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
Radek Osmulski
Simon Alibert
Alexander Soare
Remi
Akshay Kashyap
AshisGhosh
Vincent Moens
Ikko Eltociear Ashimine