tangger/lerobot
1
0
Fork 1
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix for observations with text

Browse Source
This commit is contained in:
mshukor
2025-06-01 09:35:22 +02:00
parent 496c9d0037
commit 4027d97c70
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lerobot/common/robot_devices/control_utils.py
View File

@@ -109,7 +109,7 @@ def predict_action(observation, policy, device, use_amp):
): ):
# Convert to pytorch format: channel first and float32 in [0,1] with batch dimension # Convert to pytorch format: channel first and float32 in [0,1] with batch dimension
for name in observation: for name in observation:
if isinstance(observation[name], list): if not isinstance(observation[name], torch.Tensor):
continue # VLA-like and multirobot policies include textual inputs in the observation continue # VLA-like and multirobot policies include textual inputs in the observation
if "image" in name: if "image" in name: