search

nttcslab / byol-a

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation
https://arxiv.org/abs/2103.06695
Other
205 stars 35 forks source link

a basic question：torch.randn(): argument 'size' must be tuple of ints, but found element of type list at pos 3` #6

Closed a1030076395 closed 3 years ago

a1030076395 commented 3 years ago 
Traceback (most recent call last):
  File "F:\IntellIDEA\PyCharm 2019.2.2\helpers\pydev\pydevd.py", line 2066, in <module>
    main()
  File "F:\IntellIDEA\PyCharm 2019.2.2\helpers\pydev\pydevd.py", line 2060, in main
    globals = debugger.run(setup['file'], None, None, is_module)
  File "F:\IntellIDEA\PyCharm 2019.2.2\helpers\pydev\pydevd.py", line 1411, in run
    return self._exec(is_module, entry_point_fn, module_name, file, globals, locals)
  File "F:\IntellIDEA\PyCharm 2019.2.2\helpers\pydev\pydevd.py", line 1418, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "F:\IntellIDEA\PyCharm 2019.2.2\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "E:/pythonSpace/byol-a/train.py", line 132, in <module>
    main(audio_dir=base_path + '1/', epochs=100)
  File "E:/pythonSpace/byol-a/train.py", line 112, in main
    learner = BYOLALearner(model, cfg.lr, cfg.shape,
  File "E:/pythonSpace/byol-a/train.py", line 56, in __init__
    self.learner = BYOL(model, image_size=shape, **kwargs)
  File "D:\min\envs\torch1_7_1\lib\site-packages\byol_pytorch\byol_pytorch.py", line 211, in __init__
    self.forward(torch.randn(2, 3, image_size, image_size, device=device))
TypeError: randn(): argument 'size' must be tuple of ints, but found element of type list at pos 3
daisukelab commented 3 years ago

Hi @a1030076395, I edited your comment from single-quoted error messages to triple-quoted so that everybody can read easily. I hope you could consider that if you write next time.

And what I can share with you about the error is the version of PyTorch you use. Which one are you using, please?

I could figure out you are using torch 1.7.1, I'm checking what can happen then... please hold on.

daisukelab commented 3 years ago

I found that you didn't apply the patch provided in this repo. Please follow this, from README.md:

Getting Started

  1. Download external source files, and apply a patch. Our implementation uses the following.

    curl -O https://raw.githubusercontent.com/lucidrains/byol-pytorch/2aa84ee18fafecaf35637da4657f92619e83876d/byol_pytorch/byol_pytorch.py
patch < byol_a/byol_pytorch.diff
mv byol_pytorch.py byol_a
curl -O https://raw.githubusercontent.com/daisukelab/general-learning/7b31d31637d73e1a74aec3930793bd5175b64126/MLP/torch_mlp_clf.py
mv torch_mlp_clf.py utils
a1030076395 commented 3 years ago

Hi @daisukelab Thank you for your answer, I ignored the .diff file.It can run now. your paper is super interesting, I am trying to understand the principle of augmentation module