tsurumeso

> At least in the output, it only lists one pair. Will it switch to another one after a while or do I need to do something? The pair is...

Please refer to [GET STARTED](https://pytorch.org/get-started/locally/) and reinstall PyTorch.

As for DSD100, `instruments` is a mixture of `base`, `drums`, and `other`. And `mixtures` is a mixture of `base`, `drums`, `other`, and `vocals`.

Please make sure that `vocal-remover/models/baseline.pth` is granted read permission. If you unzip the release module to your desktop, it should automatically have read permissions.

You can extend support by adding those extensions on the following lines. `input_ext` is supported extensions of input images and `output_ext` is that of output images. But I don't know...

Here it is. https://github.com/tsurumeso/vocal-remover/releases

> Where does the training loop exactly start and does it really not matter where I add that code within the training loop? Add below this line. https://github.com/tsurumeso/vocal-remover/blob/3df56690088cf6e2e62049d0c0e745aa6bba5b44/train.py#L60 > But...

Try the following command. If the output is `False`, the setup has failed. ```sh python -c "import torch; print(torch.cuda.is_available())" ```

Yeah. You should reinstall PyTorch. And also, please make sure that the latest version of NVIDIA driver for GTX 1660 is installed.

> In my test with 5 files, it starts with the second file, not with the first one and also doesn't mention any other of the 4 other files while...