train_error

[LogSSim]

Thanks for your contributions. When I run the train.py(python train.py --config-name=train_autoencoder.yaml ). There is a problem：

'''
starting from scratch
Error executing job with overrides: ['task=libero_90', 'algo=quest', 'exp_name=final', 'variant_name=block_32_ds_4', 'algo.skill_block_size=32', 'algo.downsample_factor=4', 'seed=0']
Error locating target 'quest.utils.libero_utils.build_dataset', set env var HYDRA_FULL_ERROR=1 to see chained exception.
full_key: task.dataset

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
'''

How could I fix it?

[atharvamete]

Hi,
please set HYDRA_FULL_ERROR=1 to see the full-error
you can do this by export HYDRA_FULL_ERROR=1 in terminal before running the training command

[LogSSim]

Hi, please set HYDRA_FULL_ERROR=1 to see the full-error you can do this by export HYDRA_FULL_ERROR=1 in terminal before running the training command

Thanks for your reply. I run this code in windows 10. But I got this error.
'''
Error executing job with overrides: ['task=libero_90']
Traceback (most recent call last):
File "D:\ALL_files\code\QueST\test.py", line 31, in main
for data in train_dataloader:
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch\utils\data\dataloader.py", line 701, in next
data = self._next_data()
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch\utils\data\dataloader.py", line 1465, in _next_data
return self._process_data(data)
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch\utils\data\dataloader.py", line 1491, in _process_data
data.reraise()
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch_utils.py", line 715, in reraise
raise exception
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch\utils\data_utils\worker.py", line 351, in _worker_loop
data = fetcher.fetch(index) # type: ignore[possibly-undefined]
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch\utils\data_utils\fetch.py", line 52, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch\utils\data_utils\fetch.py", line 52, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\ProgramData\anaconda3\envs\quest\lib\site-packages\torch\utils\data\dataset.py", line 350, in getitem
return self.datasets[dataset_idx][sample_idx]
File "D:\ALL_files\code\QueST\quest\utils\libero_utils.py", line 292, in getitem
return_dict = self.sequence_dataset.getitem(idx)
File "D:\ALL_files\code\QueST\quest\utils\dataset.py", line 420, in getitem
return self.get_item(index)
File "D:\ALL_files\code\QueST\quest\utils\dataset.py", line 458, in get_item
meta["obs"] = self.get_obs_sequence_from_demo(
File "D:\ALL_files\code\QueST\quest\utils\dataset.py", line 607, in get_obs_sequence_from_demo
return ObsUtils.process_obs_dict(obs)
File "D:\ALL_files\code\QueST\quest\utils\obs_utils.py", line 365, in process_obs_dict
return { k : process_obs(obs=obs, obs_key=k) for k, obs in obs_dict.items() } # shallow copy
File "D:\ALL_files\code\QueST\quest\utils\obs_utils.py", line 365, in
return { k : process_obs(obs=obs, obs_key=k) for k, obs in obs_dict.items() } # shallow copy
File "D:\ALL_files\code\QueST\quest\utils\obs_utils.py", line 350, in process_obs
obs_modality = OBS_KEYS_TO_MODALITIES[obs_key]
TypeError: 'NoneType' object is not subscriptable
'''