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

Dataset v3 (#1412)

Browse Source 
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Co-authored-by: Remi Cadene <re.cadene@gmail.com>
Co-authored-by: Tavish <tavish9.chen@gmail.com>
Co-authored-by: fracapuano <francesco.capuano@huggingface.co>
Co-authored-by: CarolinePascal <caroline8.pascal@gmail.com>
This commit is contained in:
Michel Aractingi
2025-09-15 09:53:30 +02:00
committed by GitHub
parent d602e8169c
commit f55c6e89f0
50 changed files with 4642 additions and 4092 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
tests/artifacts/datasets/save_dataset_to_safetensors.py
View File

@@ -47,38 +47,22 @@ def save_dataset_to_safetensors(output_dir, repo_id="lerobot/pusht"):
)
# save 2 first frames of first episode
i = dataset.episode_data_index["from"][0].item()
i = dataset.meta.episodes["dataset_from_index"][0]
save_file(dataset[i], repo_dir / f"frame_{i}.safetensors")
save_file(dataset[i + 1], repo_dir / f"frame_{i + 1}.safetensors")
# save 2 frames at the middle of first episode
i = int((dataset.episode_data_index["to"][0].item() - dataset.episode_data_index["from"][0].item()) / 2)
i = int(
(dataset.meta.episodes["dataset_to_index"][0] - dataset.meta.episodes["dataset_from_index"][0]) / 2
)
save_file(dataset[i], repo_dir / f"frame_{i}.safetensors")
save_file(dataset[i + 1], repo_dir / f"frame_{i + 1}.safetensors")
# save 2 last frames of first episode
i = dataset.episode_data_index["to"][0].item()
i = dataset.meta.episodes["dataset_to_index"][0]
save_file(dataset[i - 2], repo_dir / f"frame_{i - 2}.safetensors")
save_file(dataset[i - 1], repo_dir / f"frame_{i - 1}.safetensors")
# TODO(rcadene): Enable testing on second and last episode
# We currently cant because our test dataset only contains the first episode
# # save 2 first frames of second episode
# i = dataset.episode_data_index["from"][1].item()
# save_file(dataset[i], repo_dir / f"frame_{i}.safetensors")
# save_file(dataset[i + 1], repo_dir / f"frame_{i+1}.safetensors")
# # save 2 last frames of second episode
# i = dataset.episode_data_index["to"][1].item()
# save_file(dataset[i - 2], repo_dir / f"frame_{i-2}.safetensors")
# save_file(dataset[i - 1], repo_dir / f"frame_{i-1}.safetensors")
# # save 2 last frames of last episode
# i = dataset.episode_data_index["to"][-1].item()
# save_file(dataset[i - 2], repo_dir / f"frame_{i-2}.safetensors")
# save_file(dataset[i - 1], repo_dir / f"frame_{i-1}.safetensors")
if __name__ == "__main__":
for dataset in [