Simon Alibert
2f8d98b05e
Update readme ( #1570 )
...
* Cleanup badges
* Remove comment
* Remove profiling section
* Move acknowledgment
* Move citations
* Fix badge display
* Move build your robot section
* Fix nightly badge
* Revert be13b3f
* Update README.md
Co-authored-by: HUANG TZU-CHUN <tzu.chun.huang.tw@gmail.com >
Signed-off-by: Simon Alibert <75076266+aliberts@users.noreply.github.com >
* chore(docs): optimize readme for PyPI rendering
* chore(docs): move policy readme to docs folder + symlink in policy dirs
* fix(docs): max width og lerobot logo + url in citation block
---------
Signed-off-by: Simon Alibert <75076266+aliberts@users.noreply.github.com >
Co-authored-by: HUANG TZU-CHUN <tzu.chun.huang.tw@gmail.com >
Co-authored-by: Steven Palma <steven.palma@huggingface.co >
2025-08-01 17:39:39 +02:00
Adil Zouitine
4c8f002055
fix(act): disable VAE during offline inference ( #1588 )
...
Prevent VAE inference when running in offline mode. In the lerobot dataset, the presence of the 'action' field incorrectly triggers the VAE inference block. This leads to a RuntimeError due to mismatched tensor dimensions (3 vs 2) when concatenating cls_embed, robot_state_embed, and action_embed—since action_embed lacks the chunk_size dimension. Additionally, this aligns with the original paper, where variational inference is skipped during inference.
2025-07-24 17:09:12 +02:00
Steven Palma
378e1f0338
Update pre-commit-config.yaml + pyproject.toml + ceil rerun & transformer dependencies version ( #1520 )
...
* chore: update .gitignore
* chore: update pre-commit
* chore(deps): update pyproject
* fix(ci): multiple fixes
* chore: pre-commit apply
* chore: address review comments
* Update pyproject.toml
Co-authored-by: Ben Zhang <5977478+ben-z@users.noreply.github.com >
Signed-off-by: Steven Palma <imstevenpmwork@ieee.org >
* chore(deps): add todo
---------
Signed-off-by: Steven Palma <imstevenpmwork@ieee.org >
Co-authored-by: Ben Zhang <5977478+ben-z@users.noreply.github.com >
2025-07-17 14:30:20 +02:00
Adil Zouitine
91b110d806
fix(mps): gradient exploding and nan loss issues with ACT ( #1490 )
...
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co >
2025-07-15 10:28:19 +02:00
Francesco Capuano
a5e0aae13a
Fixes @torch.no_grad() usage ( #1455 )
...
* fix: decorator calls with parentheses
* fix no grad for normalize too
Signed-off-by: Francesco Capuano <74058581+fracapuano@users.noreply.github.com >
---------
Signed-off-by: Francesco Capuano <74058581+fracapuano@users.noreply.github.com >
2025-07-08 13:08:32 +02:00
Simon Alibert
d4ee470b00
Package folder structure ( #1417 )
...
* Move files
* Replace imports & paths
* Update relative paths
* Update doc symlinks
* Update instructions paths
* Fix imports
* Update grpc files
* Update more instructions
* Downgrade grpc-tools
* Update manifest
* Update more paths
* Update config paths
* Update CI paths
* Update bandit exclusions
* Remove walkthrough section
2025-07-01 16:34:46 +02:00
