You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am attempting to run the example 05_dataloading.ipynb with the bridge dataset. However, I cannot seem to get the code to run. I have tried manually changing the builder from tfds.builder(name, data_dir=data_dir) to builder = tfds.builder_from_directory(builder_dir='gs://gresearch/robotics/bridge/0.1.0/') as in the 01_example, but I still run into issues, presumably due to how the trajectories (actions) are stored.
Does anyone know how I can use the dataloader for the bridge dataset? The error in 05_dataloading.ipynb occurs at full_dataset = full_dataset.traj_map(restructure).filter(is_nonzero_length) in dataset.py.
The text was updated successfully, but these errors were encountered:
I am attempting to run the example 05_dataloading.ipynb with the bridge dataset. However, I cannot seem to get the code to run. I have tried manually changing the builder from tfds.builder(name, data_dir=data_dir) to builder = tfds.builder_from_directory(builder_dir='gs://gresearch/robotics/bridge/0.1.0/') as in the 01_example, but I still run into issues, presumably due to how the trajectories (actions) are stored.
Does anyone know how I can use the dataloader for the bridge dataset? The error in 05_dataloading.ipynb occurs at full_dataset = full_dataset.traj_map(restructure).filter(is_nonzero_length) in dataset.py.
I am attempting to run the example 05_dataloading.ipynb with the bridge dataset. However, I cannot seem to get the code to run. I have tried manually changing the builder from
tfds.builder(name, data_dir=data_dir)
tobuilder = tfds.builder_from_directory(builder_dir='gs://gresearch/robotics/bridge/0.1.0/')
as in the 01_example, but I still run into issues, presumably due to how the trajectories (actions) are stored.Does anyone know how I can use the dataloader for the bridge dataset? The error in 05_dataloading.ipynb occurs at
full_dataset = full_dataset.traj_map(restructure).filter(is_nonzero_length)
in dataset.py.The text was updated successfully, but these errors were encountered: