admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-23 20:50:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

style

Browse Source
This commit is contained in:
Jade Choghari
2025-12-01 13:47:15 +01:00
parent d22fa6446b
commit 8d861fe94b
2 changed files with 34 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/using_dataset_tools.mdx
+1
View File
@@ -124,6 +124,7 @@ lerobot-edit-dataset \
``` ```
**Parameters:** **Parameters:**
- `output_dir`: Directory where videos will be saved (default: `outputs/converted_videos`) - `output_dir`: Directory where videos will be saved (default: `outputs/converted_videos`)
- `vcodec`: Video codec to use - options: `h264`, `hevc`, `libsvtav1` (default: `libsvtav1`) - `vcodec`: Video codec to use - options: `h264`, `hevc`, `libsvtav1` (default: `libsvtav1`)
- `pix_fmt`: Pixel format - options: `yuv420p`, `yuv444p` (default: `yuv420p`) - `pix_fmt`: Pixel format - options: `yuv420p`, `yuv444p` (default: `yuv420p`)
src/lerobot/scripts/lerobot_edit_dataset.py
+6 -2
View File
@@ -389,7 +389,9 @@ def process_single_episode(
imgs_dir = output_dir / "images" / dataset.repo_id.replace("/", "_") / f"episode_{episode_index:06d}" imgs_dir = output_dir / "images" / dataset.repo_id.replace("/", "_") / f"episode_{episode_index:06d}"
# Create video filename with encoding parameters # Create video filename with encoding parameters
video_filename = f"{dataset.repo_id.replace('/', '_')}_ep{episode_index:06d}_{vcodec}_{pix_fmt}_g{g}_crf{crf}.mp4" video_filename = (
f"{dataset.repo_id.replace('/', '_')}_ep{episode_index:06d}_{vcodec}_{pix_fmt}_g{g}_crf{crf}.mp4"
)
video_path = output_dir / "videos" / dataset.repo_id.replace("/", "_") / video_filename video_path = output_dir / "videos" / dataset.repo_id.replace("/", "_") / video_filename
# Save episode images # Save episode images
@@ -455,7 +457,9 @@ def convert_dataset_to_videos(
if episode_indices is None: if episode_indices is None:
episode_indices = list(range(num_episodes)) episode_indices = list(range(num_episodes))
logging.info(f"Processing {len(episode_indices)} episodes from {dataset.repo_id} with {num_workers} workers") logging.info(
f"Processing {len(episode_indices)} episodes from {dataset.repo_id} with {num_workers} workers"
)
# Process episodes in parallel # Process episodes in parallel
with ThreadPoolExecutor(max_workers=num_workers) as executor: with ThreadPoolExecutor(max_workers=num_workers) as executor: