Error While Training the Model as per README Instructions.

[NakataKoo]

First of all, I thank you so much for this great project. You have done a really tremendous job, and I am so full of anticipation about exploring and using this model.

I was following the instructions provided in the README to train the model, including the environment setup and dataset acquisition, but I encountered an error during the process. Below are the details:

Error:

1. After building the environment and acquiring the data set, the following commands were executed:
   PYTHONPATH=. python train.py exp=train_msdm

2. Then I got the following error:

Traceback (most recent call last):
  File "/raid/m236866/multi-source-diffusion-models/train.py", line 4, in <module>
    import pytorch_lightning as pl
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/pytorch_lightning/__init__.py", line 34, in <module>
    from pytorch_lightning.callbacks import Callback  # noqa: E402
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/pytorch_lightning/callbacks/__init__.py", line 25, in <module>
    from pytorch_lightning.callbacks.progress import ProgressBarBase, RichProgressBar, TQDMProgressBar
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/pytorch_lightning/callbacks/progress/__init__.py", line 22, in <module>
    from pytorch_lightning.callbacks.progress.rich_progress import RichProgressBar  # noqa: F401
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/pytorch_lightning/callbacks/progress/rich_progress.py", line 20, in <module>
    from torchmetrics.utilities.imports import _compare_version
ImportError: cannot import name '_compare_version' from 'torchmetrics.utilities.imports' (/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/torchmetrics/utilities/imports.py)

3. Then, I installed torchmetrics and executed it again, and the following error occurred:

/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: 'libc10_cuda.so: cannot open shared object file: No such file or directory'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
Enter run name: first-test-of-train-0525
[2024-05-25 21:11:39,620][main.utils][INFO] - Disabling python warnings! <config.ignore_warnings=True>
Global seed set to 12345
[2024-05-25 21:11:39,622][__main__][INFO] - Instantiating datamodule <main.module_base.DatamoduleWithValidation>.
Error executing job with overrides: ['exp=train_msdm']
Error locating target 'main.data.MultiSourceDataset', see chained exception above.
full_key: datamodule.train_dataset

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

4. Finally, I tried the following and executed it again:

conda install -c conda-forge cudatoolkit=11.3 cudnn=8.2
conda install -c conda-forge libjpeg libpng
pip uninstall torchvision
pip install torchvision
export HYDRA_FULL_ERROR=1

5. Then the following error occurred:

/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: 'libc10_cuda.so: cannot open shared object file: No such file or directory'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
Enter run name: test
[2024-05-25 21:13:40,990][main.utils][INFO] - Disabling python warnings! <config.ignore_warnings=True>
Global seed set to 12345
[2024-05-25 21:13:40,992][__main__][INFO] - Instantiating datamodule <main.module_base.DatamoduleWithValidation>.
Error executing job with overrides: ['exp=train_msdm']
Traceback (most recent call last):
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 639, in _locate
    obj = getattr(obj, part)
AttributeError: module 'main' has no attribute 'data'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 645, in _locate
    obj = import_module(mod)
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1030, in _gcd_import
  File "<frozen importlib._bootstrap>", line 1007, in _find_and_load
  File "<frozen importlib._bootstrap>", line 986, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 680, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 850, in exec_module
  File "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removed
  File "/raid/m236866/multi-source-diffusion-models/main/data.py", line 11, in <module>
    import av
ModuleNotFoundError: No module named 'av'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 134, in _resolve_target
    target = _locate(target)
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 648, in _locate
    raise ImportError(
ImportError: Error loading 'main.data.MultiSourceDataset':
ModuleNotFoundError("No module named 'av'")
Are you sure that 'data' is importable from module 'main'?

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/raid/m236866/multi-source-diffusion-models/train.py", line 99, in <module>
    main()
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/main.py", line 90, in decorated_main
    _run_hydra(
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 389, in _run_hydra
    _run_app(
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 452, in _run_app
    run_and_report(
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 216, in run_and_report
    raise ex
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 213, in run_and_report
    return func()
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/utils.py", line 453, in <lambda>
    lambda: hydra.run(
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/hydra.py", line 132, in run
    _ = ret.return_value
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/core/utils.py", line 260, in return_value
    raise self._return_value
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job
    ret.return_value = task_function(task_cfg)
  File "/raid/m236866/multi-source-diffusion-models/train.py", line 28, in main
    datamodule = hydra.utils.instantiate(config.datamodule, _convert_="partial")
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 222, in instantiate
    return instantiate_node(
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 334, in instantiate_node
    value = instantiate_node(
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 325, in instantiate_node
    _target_ = _resolve_target(node.get(_Keys.TARGET), full_key)
  File "/home/m236866/.conda/envs/msdm/lib/python3.9/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 139, in _resolve_target
    raise InstantiationException(msg) from e
hydra.errors.InstantiationException: Error locating target 'main.data.MultiSourceDataset', see chained exception above.
full_key: datamodule.train_dataset

I would greatly appreciate any guidance or solutions you could provide to resolve this issue.

Thank you once again for your incredible work.

[syl4356]

Hi, I suffered from the same problem. It was resolved by installing av.

pip install av