ydy0615/lerobot-clone
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-31 19:01:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: replace hard-coded action values with constants throughout all the source code (#2055)

Browse Source 
* chore: replace hard-coded 'action' values with constants throughout all the source code

* chore(tests): replace hard-coded action values with constants throughout all the test code
This commit is contained in:
Steven Palma
2025-09-26 13:33:18 +02:00
committed by GitHub
parent 9627765ce2
commit d2782cf66b
47 changed files with 269 additions and 255 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/lerobot/scripts/lerobot_eval.py
View File

@@ -81,7 +81,7 @@ from lerobot.envs.utils import (
from lerobot.policies.factory import make_policy, make_pre_post_processors
from lerobot.policies.pretrained import PreTrainedPolicy
from lerobot.processor import PolicyAction, PolicyProcessorPipeline
from lerobot.utils.constants import OBS_STR
from lerobot.utils.constants import ACTION, OBS_STR
from lerobot.utils.io_utils import write_video
from lerobot.utils.random_utils import set_seed
from lerobot.utils.utils import (
@@ -213,7 +213,7 @@ def rollout(
# Stack the sequence along the first dimension so that we have (batch, sequence, *) tensors.
ret = {
"action": torch.stack(all_actions, dim=1),
ACTION: torch.stack(all_actions, dim=1),
"reward": torch.stack(all_rewards, dim=1),
"success": torch.stack(all_successes, dim=1),
"done": torch.stack(all_dones, dim=1),
@@ -440,14 +440,14 @@ def _compile_episode_data(
"""
ep_dicts = []
total_frames = 0
for ep_ix in range(rollout_data["action"].shape[0]):
for ep_ix in range(rollout_data[ACTION].shape[0]):
# + 2 to include the first done frame and the last observation frame.
num_frames = done_indices[ep_ix].item() + 2
total_frames += num_frames
# Here we do `num_frames - 1` as we don't want to include the last observation frame just yet.
ep_dict = {
"action": rollout_data["action"][ep_ix, : num_frames - 1],
ACTION: rollout_data[ACTION][ep_ix, : num_frames - 1],
"episode_index": torch.tensor([start_episode_index + ep_ix] * (num_frames - 1)),
"frame_index": torch.arange(0, num_frames - 1, 1),
"timestamp": torch.arange(0, num_frames - 1, 1) / fps,