Sattwik Kumar Sahu

Yes, I am logged in.

Hi, I ran the example streaming dataset code you provided above, it gives me the following error:

DataFilesNotFoundError                    Traceback (most recent call last)
Cell In[2], line 5
      3 # Streams directly from the Hugging Face Hub, without downloading the dataset into disk or loading into memory
      4 repo_id = "yaak-ai/L2D-v3"
----> 5 dataset = StreamingLeRobotDataset(repo_id)

File ~/sattwik/projects/robot-learning/act2/.venv/lib/python3.12/site-packages/lerobot/datasets/streaming_dataset.py:152, in StreamingLeRobotDataset.__init__(self, repo_id, root, episodes, image_transforms, delta_timestamps, tolerance_s, revision, force_cache_sync, streaming, buffer_size, max_num_shards, seed, rng, shuffle)
    149     self.delta_timestamps = delta_timestamps
    150     self.delta_indices = get_delta_indices(self.delta_timestamps, self.fps)
--> 152 self.hf_dataset: datasets.IterableDataset = load_dataset(
    153     self.repo_id if not self.streaming_from_local else str(self.root),
    154     split="train",
    155     streaming=self.streaming,
    156     data_files="data/*/*.parquet",
    157     revision=self.revision,
    158 )
    160 self.num_shards = min(self.hf_dataset.num_shards, max_num_shards)

File ~/sattwik/projects/robot-learning/act2/.venv/lib/python3.12/site-packages/datasets/load.py:1392, in load_dataset(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, keep_in_memory, save_infos, revision, token, streaming, num_proc, storage_options, **config_kwargs)
   1387 verification_mode = VerificationMode(
   1388     (verification_mode or VerificationMode.BASIC_CHECKS) if not save_infos else VerificationMode.ALL_CHECKS
   1389 )
   1391 # Create a dataset builder
-> 1392 builder_instance = load_dataset_builder(
   1393     path=path,
   1394     name=name,
   1395     data_dir=data_dir,
   1396     data_files=data_files,
   1397     cache_dir=cache_dir,
   1398     features=features,
   1399     download_config=download_config,
   1400     download_mode=download_mode,
   1401     revision=revision,
   1402     token=token,
   1403     storage_options=storage_options,
   1404     **config_kwargs,
   1405 )
   1407 # Return iterable dataset in case of streaming
   1408 if streaming:

File ~/sattwik/projects/robot-learning/act2/.venv/lib/python3.12/site-packages/datasets/load.py:1132, in load_dataset_builder(path, name, data_dir, data_files, cache_dir, features, download_config, download_mode, revision, token, storage_options, **config_kwargs)
   1130 if features is not None:
   1131     features = _fix_for_backward_compatible_features(features)
-> 1132 dataset_module = dataset_module_factory(
   1133     path,
   1134     revision=revision,
   1135     download_config=download_config,
   1136     download_mode=download_mode,
   1137     data_dir=data_dir,
   1138     data_files=data_files,
   1139     cache_dir=cache_dir,
   1140 )
   1141 # Get dataset builder class
   1142 builder_kwargs = dataset_module.builder_kwargs

File ~/sattwik/projects/robot-learning/act2/.venv/lib/python3.12/site-packages/datasets/load.py:1025, in dataset_module_factory(path, revision, download_config, download_mode, data_dir, data_files, cache_dir, **download_kwargs)
   1023     raise ConnectionError(f"Couldn't reach the Hugging Face Hub for dataset '{path}': {e1}") from None
   1024 if isinstance(e1, (DataFilesNotFoundError, DatasetNotFoundError, EmptyDatasetError)):
-> 1025     raise e1 from None
   1026 if isinstance(e1, FileNotFoundError):
   1027     raise FileNotFoundError(
   1028         f"Couldn't find any data file at {relative_to_absolute_path(path)}. "
   1029         f"Couldn't find '{path}' on the Hugging Face Hub either: {type(e1).__name__}: {e1}"
   1030     ) from None

File ~/sattwik/projects/robot-learning/act2/.venv/lib/python3.12/site-packages/datasets/load.py:1004, in dataset_module_factory(path, revision, download_config, download_mode, data_dir, data_files, cache_dir, **download_kwargs)
    994     else:
    995         use_exported_dataset_infos = True
    996     return HubDatasetModuleFactory(
    997         path,
    998         commit_hash=commit_hash,
    999         data_dir=data_dir,
   1000         data_files=data_files,
   1001         download_config=download_config,
   1002         download_mode=download_mode,
   1003         use_exported_dataset_infos=use_exported_dataset_infos,
-> 1004     ).get_module()
   1005 except GatedRepoError as e:
   1006     message = f"Dataset '{path}' is a gated dataset on the Hub."

File ~/sattwik/projects/robot-learning/act2/.venv/lib/python3.12/site-packages/datasets/load.py:638, in HubDatasetModuleFactory.get_module(self)
    631     patterns = get_data_patterns(base_path, download_config=self.download_config)
    632 data_files = DataFilesDict.from_patterns(
    633     patterns,
    634     base_path=base_path,
    635     allowed_extensions=ALL_ALLOWED_EXTENSIONS,
    636     download_config=self.download_config,
    637 )
--> 638 module_name, default_builder_kwargs = infer_module_for_data_files(
    639     data_files=data_files,
    640     path=self.name,
    641     download_config=self.download_config,
    642 )
    643 data_files = data_files.filter(
    644     extensions=_MODULE_TO_EXTENSIONS[module_name], file_names=_MODULE_TO_METADATA_FILE_NAMES[module_name]
    645 )
    646 module_path, _ = _PACKAGED_DATASETS_MODULES[module_name]

File ~/sattwik/projects/robot-learning/act2/.venv/lib/python3.12/site-packages/datasets/load.py:300, in infer_module_for_data_files(data_files, path, download_config)
    298     raise ValueError(f"Couldn't infer the same data file format for all splits. Got {split_modules}")
    299 if not module_name:
--> 300     raise DataFilesNotFoundError("No (supported) data files found" + (f" in {path}" if path else ""))
    301 return module_name, default_builder_kwargs

DataFilesNotFoundError: No (supported) data files found in yaak-ai/L2D-v3