pi0.5-pick_object-s6svwdy45b

pi0.5 model - 🧪 phosphobot training pipeline

• Dataset: pavel-kurnosov/pick_object
• Wandb run id: None

Error Traceback

We faced an issue while training your model.

Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/app/.venv/lib/python3.11/site-packages/torch/utils/data/_utils/worker.py", line 349, in _worker_loop
    data = fetcher.fetch(index)  # type: ignore[possibly-undefined]
           ^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 52, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
            ~~~~~~~~~~~~^^^^^
  File "/openpi-source/src/openpi/training/data_loader.py", line 58, in __getitem__
    return self._transform(self._dataset[index])
                           ~~~~~~~~~~~~~^^^^^^^
  File "/openpi-source/src/openpi/training/data_loader.py", line 58, in __getitem__
    return self._transform(self._dataset[index])
                           ~~~~~~~~~~~~~^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/lerobot/datasets/lerobot_dataset.py", line 720, in __getitem__
    video_frames = self._query_videos(query_timestamps, ep_idx)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/lerobot/datasets/lerobot_dataset.py", line 692, in _query_videos
    frames = decode_video_frames(video_path, query_ts, self.tolerance_s, self.video_backend)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/lerobot/datasets/video_utils.py", line 66, in decode_video_frames
    return decode_video_frames_torchcodec(video_path, timestamps, tolerance_s)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/lerobot/datasets/video_utils.py", line 195, in decode_video_frames_torchcodec
    decoder = VideoDecoder(video_path, device=device, seek_mode="approximate")
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/torchcodec/decoders/_video_decoder.py", line 89, in __init__
    self._decoder = create_decoder(source=source, seek_mode=seek_mode)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/torchcodec/decoders/_decoder_utils.py", line 29, in create_decoder
    return core.create_from_file(str(source), seek_mode)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.11/site-packages/torch/_ops.py", line 756, in __call__
    return self._op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Could not open input file: /data/hf_cache/lerobot/pavel-kurnosov/pick_object/videos/chunk-000/observation.images.secondary_0/episode_000001.mp4 No such file or directory

Training parameters

{
  "save_interval": 100,
  "num_train_steps": 500,
  "batch_size": 32,
  "seed": 42,
  "data.image_keys": [
    "observation.images.main",
    "observation.images.secondary_0"
  ]
}

📖 Get Started: docs.phospho.ai

🤖 Get your robot: robots.phospho.ai