admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-22 12:09:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Small docstring fix in diffusion configuration (#2847)

Browse Source
This commit is contained in:
jwang078
2026-02-03 13:19:00 -05:00
committed by GitHub
parent a6370dd783
commit 0f39248445
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lerobot/policies/diffusion/configuration_diffusion.py
+1 -1
View File
@@ -64,7 +64,7 @@ class DiffusionConfig(PreTrainedConfig):
use_group_norm: Whether to replace batch normalization with group normalization in the backbone. use_group_norm: Whether to replace batch normalization with group normalization in the backbone.
The group sizes are set to be about 16 (to be precise, feature_dim // 16). The group sizes are set to be about 16 (to be precise, feature_dim // 16).
spatial_softmax_num_keypoints: Number of keypoints for SpatialSoftmax. spatial_softmax_num_keypoints: Number of keypoints for SpatialSoftmax.
use_separate_rgb_encoders_per_camera: Whether to use a separate RGB encoder for each camera view. use_separate_rgb_encoder_per_camera: Whether to use a separate RGB encoder for each camera view.
down_dims: Feature dimension for each stage of temporal downsampling in the diffusion modeling Unet. down_dims: Feature dimension for each stage of temporal downsampling in the diffusion modeling Unet.
You may provide a variable number of dimensions, therefore also controlling the degree of You may provide a variable number of dimensions, therefore also controlling the degree of
downsampling. downsampling.