RuntimeError: output with device cpu and dtype Byte doesn't match the desired device cpu and dtype Float

[aisosalo]

RuntimeError: output with device cpu and dtype Byte doesn't match the desired device cpu and dtype Float when running https://github.com/MIPT-Oulu/Collagen/blob/master/examples/cnn_cifar10/train.py

Traceback:

Traceback (most recent call last):
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/hydra/main.py", line 24, in decorated_main
    strict=strict,
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/hydra/_internal/utils.py", line 174, in run_hydra
    overrides=args.overrides,
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/hydra/_internal/hydra.py", line 86, in run
    job_subdir_key=None,
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/hydra/plugins/common/utils.py", line 109, in run_job
    ret.return_value = task_function(task_cfg)
  File "/mnt/myusername/PycharmProjectFiles/Collagen/examples/cnn_cifar10/train.py", line 91, in main
    strategy.run()
  File "/mnt/myusername/PycharmProjectFiles/Collagen/collagen/strategies/_strategy.py", line 259, in run
    self.__data_provider.sample(**self.__num_samples_by_stage[stage][model_name])
  File "/mnt/myusername/PycharmProjectFiles/Collagen/collagen/data/_dataprovider.py", line 53, in sample
    list_samples.append(self.__sample(il_name, k))
  File "/mnt/myusername/PycharmProjectFiles/Collagen/collagen/data/_dataprovider.py", line 73, in __sample
    samples = self.__loaders[itemloader_name].sample(k)
  File "/mnt/myusername/PycharmProjectFiles/Collagen/collagen/data/_itemloader.py", line 161, in sample
    batch = next(self.__iter_loader)
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 819, in __next__
    return self._process_data(data)
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data
    data.reraise()
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/torch/_utils.py", line 369, in reraise
    raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/mnt/myusername/PycharmProjectFiles/Collagen/collagen/data/_dataset.py", line 67, in __getitem__
    entry = self.parse_item_cb(self.root, entry, self.transform, **self.parser_kwargs)
  File "/mnt/myusername/PycharmProjectFiles/Collagen/examples/cnn_cifar10/utils.py", line 10, in parse_item
    trf_data = trf({'image': img}, normalize=True, **stats)
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/solt/core/_core.py", line 152, in __call__
    as_dict=as_dict, scale_keypoints=scale_keypoints, normalize=normalize, mean=mean, std=std,
  File "/home/myusername/anaconda3/envs/py36_env/lib/python3.6/site-packages/solt/core/_data.py", line 273, in to_torch
    img.sub_(mean)
RuntimeError: output with device cpu and dtype Byte doesn't match the desired device cpu and dtype Float

System:

Linux-5.3.0-51-generic-x86_64-with-debian-buster-sid 
Python 3.6.10 |Anaconda, Inc.| (default, Mar 25 2020, 23:51:54) 
[GCC 7.3.0] 
PyTorch 1.2.0

[hoanghng]

Based on the logs, it seems to the SOLT lib. I tested the example using SOLT 0.1.9 on GPU.

[aisosalo]

Did you get the same error or everything works fine on your setup? I am running SOLT 0.1.9.