admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-27 22:49:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(policy): use pretrained vision encoder weights by default for diffusion and vqbet (#3202)

Browse Source 
* feat: add pretrained vision encoder weights for diffusion and vqbet

* fix test by re-generating artifacts

---------

Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
This commit is contained in:
Ville Kuosmanen
2026-05-07 11:10:38 +01:00
committed by GitHub
parent a0e52d52fe
commit eaf0218bc8
6 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lerobot/policies/diffusion/configuration_diffusion.py
+5 -5
View File
@@ -100,8 +100,8 @@ class DiffusionConfig(PreTrainedConfig):
# Inputs / output structure.
n_obs_steps: int = 2
horizon: int = 16
n_action_steps: int = 8
horizon: int = 64
n_action_steps: int = 32
normalization_mapping: dict[str, NormalizationMode] = field(
default_factory=lambda: {
@@ -122,10 +122,10 @@ class DiffusionConfig(PreTrainedConfig):
crop_ratio: float = 1.0
crop_shape: tuple[int, int] | None = None
crop_is_random: bool = True
pretrained_backbone_weights: str | None = None
use_group_norm: bool = True
pretrained_backbone_weights: str | None = "ResNet18_Weights.IMAGENET1K_V1"
use_group_norm: bool = False
spatial_softmax_num_keypoints: int = 32
use_separate_rgb_encoder_per_camera: bool = False
use_separate_rgb_encoder_per_camera: bool = True
# Unet.
down_dims: tuple[int, ...] = (512, 1024, 2048)
kernel_size: int = 5
src/lerobot/policies/vqbet/configuration_vqbet.py
+2 -2
View File
@@ -97,8 +97,8 @@ class VQBeTConfig(PreTrainedConfig):
vision_backbone: str = "resnet18"
crop_shape: tuple[int, int] | None = (84, 84)
crop_is_random: bool = True
pretrained_backbone_weights: str | None = None
use_group_norm: bool = True
pretrained_backbone_weights: str | None = "ResNet18_Weights.IMAGENET1K_V1"
use_group_norm: bool = False
spatial_softmax_num_keypoints: int = 32
# VQ-VAE
n_vqvae_training_steps: int = 20000