5 Commits

Author	SHA1	Message	Date
Steven Palma	5b541c042d	refactor(policy): evo1 GPU-batched preprocessing + vectorized attention masking + remove dead code	2026-07-02 10:47:50 +02:00
javadcc_mac	25556ceefe	fix(evo1): move LIBERO padding into policy processors	2026-06-21 15:58:38 +08:00
javadcc_mac	a5e6409985	fix(evo1): finalize policy guide alignment	2026-05-11 21:51:41 +08:00
javadcc_mac	48269dddb3	fix(evo1): infer batch size after normalizing image dims ... `_collect_image_batches` read `batch_size = batch[camera_keys[0]].shape[0]` before normalizing per-camera tensors to `(B, C, H, W)`. For an unbatched `(C, H, W)` input (which the function tries to support via the `image.dim() == 3` branch), this picked up the channel count `C` instead of the real batch size, making the subsequent per-sample loop iterate `C` times and indexing go out of bounds. Normalize each camera tensor up-front, then read `batch_size` from the normalized batch dim. Adds `test_collect_image_batches_handles_unbatched_chw` covering the regression. Reported by Copilot review on huggingface/lerobot#3545.	2026-05-10 11:29:23 +08:00
javadcc_mac	8df8d3d866	feat(policies): add EVO1 policy	2026-05-09 21:39:19 +08:00