Training error in dpt_vit-b16

[a227799770055]

Hi @zhyever
I want to train the model with my custom dataset in dpt_vit-b16_kitti, and I encounter the error as below.
It's seem that can not find the pretrain file nfs/checkpoints/jx_vit_base_p16_224-80ecf9dd.pth. Where can I download the file and which path should I put the file?

Traceback (most recent call last): File "./tools/train.py", line 168, in <module> main() File "./tools/train.py", line 135, in main model.init_weights() File "/home/insign2/.local/lib/python3.8/site-packages/mmcv/runner/base_module.py", line 117, in init_weights m.init_weights() File "/home/insign2/work/Monocular-Depth-Estimation-Toolbox/depth/models/backbones/vit.py", line 282, in init_weights checkpoint = CheckpointLoader.load_checkpoint( File "/home/insign2/.local/lib/python3.8/site-packages/mmcv/runner/checkpoint.py", line 314, in load_checkpoint return checkpoint_loader(filename, map_location) # type: ignore File "/home/insign2/.local/lib/python3.8/site-packages/mmcv/runner/checkpoint.py", line 333, in load_from_local raise FileNotFoundError(f'{filename} can not be found.') FileNotFoundError: nfs/checkpoints/jx_vit_base_p16_224-80ecf9dd.pth can not be found. ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 151529) of binary: /usr/bin/python3 Traceback (most recent call last): File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/home/insign2/.local/lib/python3.8/site-packages/torch/distributed/launch.py", line 195, in <module> main() File "/home/insign2/.local/lib/python3.8/site-packages/torch/distributed/launch.py", line 191, in main launch(args) File "/home/insign2/.local/lib/python3.8/site-packages/torch/distributed/launch.py", line 176, in launch run(args) File "/home/insign2/.local/lib/python3.8/site-packages/torch/distributed/run.py", line 753, in run elastic_launch( File "/home/insign2/.local/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 132, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/home/insign2/.local/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 246, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

[Z-chocking]

You should download the pre-trained models.Please refer the DPT's markdown file.

[a227799770055]

@Z-chocking thank you!

[a227799770055]

@zhyever
Hi I got an other error when training.
How should I solve the problem?

 Traceback (most recent call last):
  File "./tools/train.py", line 168, in <module>
    main()
  File "./tools/train.py", line 157, in main
    train_depther(
  File "/home/insign/work/Monocular-Depth-Estimation-Toolbox/depth/apis/train.py", line 121, in train_depther
    runner.run(data_loaders, cfg.workflow)
  File "/home/insign/.local/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 136, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/home/insign/.local/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 49, in train
    for i, data_batch in enumerate(self.data_loader):
  File "/home/insign/.local/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 628, in __next__
    data = self._next_data()
  File "/home/insign/.local/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1333, in _next_data
    return self._process_data(data)
  File "/home/insign/.local/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1359, in _process_data
    data.reraise()
  File "/home/insign/.local/lib/python3.8/site-packages/torch/_utils.py", line 542, in reraise
    raise RuntimeError(msg) from None
RuntimeError: Caught UnicodeDecodeError in DataLoader worker process 0.