Seungjae Lee
|
aaa4c65fb9
|
Merge pull request #6 from huggingface/main
Merge from hf lerobot main branch
|
2024-06-05 14:29:00 -04:00 |
jayLEE0301
|
8b3683ff21
|
Merge branch 'main' of https://github.com/jayLEE0301/lerobot
|
2024-06-05 14:22:08 -04:00 |
|
jayLEE0301
|
bc10e34700
|
change discretize_step -> n_vqvae_training_steps
|
2024-06-05 14:05:50 -04:00 |
|
jayLEE0301
|
fd8fc11342
|
make the code to handle dynamically
|
2024-06-05 14:01:40 -04:00 |
|
jayLEE0301
|
eedc131d27
|
move if self.vqvae_model.check_discretized(): part inside def pretrain_vqvae
|
2024-06-05 13:56:21 -04:00 |
|
jayLEE0301
|
1778dee9ab
|
delete some short functions
|
2024-06-05 13:47:06 -04:00 |
|
jayLEE0301
|
975da28461
|
change loss fn name, remove unnecessary resizing part
|
2024-06-05 13:36:54 -04:00 |
|
jayLEE0301
|
eaf0af0ac6
|
remove unused parts
|
2024-06-05 13:09:37 -04:00 |
|
jayLEE0301
|
f69d552480
|
remove unnecessary resizing parts
|
2024-06-05 11:57:41 -04:00 |
|
jayLEE0301
|
63d198cf0a
|
change explanations
|
2024-06-05 11:52:32 -04:00 |
|
jayLEE0301
|
36525b3d2e
|
remove .cuda() parts
|
2024-06-05 11:46:32 -04:00 |
|
jayLEE0301
|
75bdcaab81
|
remove unused parts in def discretize
|
2024-06-05 11:36:10 -04:00 |
|
jayLEE0301
|
06d3eb40e1
|
remove redundant explanations
|
2024-06-05 11:33:19 -04:00 |
|
jayLEE0301
|
78da71c31b
|
add sequentially select options
|
2024-06-05 11:29:08 -04:00 |
|
jayLEE0301
|
dbc029b353
|
change confusing terms regarding action_tokens
|
2024-06-05 11:23:24 -04:00 |
|
jayLEE0301
|
8c775c94fc
|
simplified action stacking part
|
2024-06-05 11:20:13 -04:00 |
Alexander Soare
|
1eb4bfe2e4
|
Fix videos_dir documentation (#247)
|
2024-06-05 08:25:20 +01:00 |
|
jayLEE0301
|
c4c5977f37
|
minor: nit
|
2024-06-04 20:45:26 -04:00 |
|
jayLEE0301
|
6d72847bfe
|
change n_action_pred_chunk -> action_chunk_size
|
2024-06-04 17:59:49 -04:00 |
|
jayLEE0301
|
bc9e6874fc
|
replace forward part with concise one
|
2024-06-04 17:41:34 -04:00 |
|
jayLEE0301
|
18b19b95f8
|
fix obs_projector to rgb_feature_projector, replace notimplementederror to assert
|
2024-06-04 17:20:57 -04:00 |
|
jayLEE0301
|
9f109538d9
|
fix typo
|
2024-06-04 17:14:26 -04:00 |
|
jayLEE0301
|
1f59e45f11
|
fix Phase -> Training Phase
|
2024-06-04 17:12:46 -04:00 |
|
jayLEE0301
|
833d440ebf
|
fix header -> head, bind pred -> bin prediction
|
2024-06-04 17:10:39 -04:00 |
|
jayLEE0301
|
87842c0d19
|
add explanaitons for n_different_codes, n_different_combinations
|
2024-06-04 17:05:04 -04:00 |
|
jayLEE0301
|
6012b4c859
|
change loss to loss_dict (vq-bet policy output name)
|
2024-06-04 16:59:02 -04:00 |
|
jayLEE0301
|
0657c0c6c1
|
fix typo
|
2024-06-04 16:53:49 -04:00 |
|
Alexander Soare
|
21f222fa1d
|
Add out_dir option to eval (#244)
|
2024-06-04 21:01:53 +02:00 |
amandip7
|
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 |
Ruijie
|
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 |
|
jayLEE0301
|
6d9a65ca39
|
remove check_discretized at VQBeTPolicy, and directly use the function in class VqVae
|
2024-06-03 18:29:26 -04:00 |
|
jayLEE0301
|
651d9f46e5
|
remove .discretized, and add register_buffer
|
2024-06-03 18:25:30 -04:00 |
|
jayLEE0301
|
f0508d02b9
|
add self.reset() at the bottom of __init__ in class VQBeTPolicy
|
2024-06-03 17:45:59 -04:00 |
|
jayLEE0301
|
a33fbd4d44
|
SpatialSoftmax from modeling_diffusion.py
|
2024-06-03 17:43:11 -04:00 |
Simon Alibert
|
bd3111f28b
|
Fix `visualize_dataset.py --help` (#241)
|
2024-06-03 16:35:16 +02:00 |
|
Alexander Soare
|
cf15cba5fc
|
Remove redundant slicing operation in Diffusion Policy (#240)
|
2024-06-03 13:04:24 +01:00 |
jganitzer
|
042e193995
|
Typo in examples\4_train_policy_with_script.md (#235)
|
2024-05-31 18:14:14 +01:00 |
Remi
|
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 |
Radek Osmulski
|
504d2aaf48
|
add EpisodeAwareSampler (#217)
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
|
2024-05-31 13:43:47 +01:00 |
|
Radek Osmulski
|
83f4f7f7e8
|
Add precision param to format_big_number (#232)
|
2024-05-31 10:19:01 +02:00 |
|
Alexander Soare
|
633115d861
|
Fix chaining in MultiLerobotDataset (#233)
|
2024-05-31 09:03:28 +01:00 |
|
Alexander Soare
|
57fb5fe8a6
|
Improve documentation on VAE encoder inputs (#215)
|
2024-05-30 19:16:44 +02:00 |
|
Alexander Soare
|
0b51a335bc
|
Add a test for MultiLeRobotDataset making sure it produces all frames. (#230)
Co-authored-by: Remi <re.cadene@gmail.com>
|
2024-05-30 17:46:25 +01:00 |
|
Alexander Soare
|
111cd58f8a
|
Add `MultiLerobotDataset` for training with multiple `LeRobotDataset`s (#229)
|
2024-05-30 16:12:21 +01:00 |
|
Remi
|
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 |
|
Remi
|
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 |
|
Simon Alibert
|
13310681b1
|
Enable cuda for end-to-end tests (#222)
|
2024-05-29 23:02:23 +02:00 |
|
Alexander Soare
|
3d625ae6d3
|
Handle `crop_shape=None` in Diffusion Policy (#219)
|
2024-05-28 18:27:33 +01:00 |
|
Alexander Soare
|
e3b9f1c19b
|
Add resume training (#205)
Co-authored-by: Remi <re.cadene@gmail.com>
|
2024-05-28 12:04:23 +01:00 |
|
Simon Alibert
|
7ec76ee235
|
Fix nightly builds (#216)
|
2024-05-28 10:43:34 +02:00 |