Daisuke Niizumi

Just FYI, I applied work-around with local change borrowing: https://github.com/pytorch/vision/blob/master/torchvision/models/utils.py ```python try: from torch.hub import load_state_dict_from_url except ImportError: from torch.utils.model_zoo import load_url as load_state_dict_from_url ``` (Just dunno if applying this...

Hi, I could successfully train my own. You can simply edit squeeze.config created by `python ../../main/config/create_config.py`. Check it first, it is easy to customize. Regarding pretrained model, you can find...

Hi, training code doesn't allow to have empty label, then you need to remove images which have zero class label from your train/valid lists. (I already experienced that training stopped...

Hello, this is as far as I tried today: - I could successfully download the master.zip by `wget https://github.com/karoldvl/ESC-50/archive/master.zip`. - Downloading from the `dataverse.harvard.edu` is also OK, and it's 245MB...

Hi @Huiimin5, Thank you for your comments and attention. I'm afraid, but we have moved on to the new evaluation package [EVAR](https://github.com/nttcslab/eval-audio-repr). Could you refer to it, please? It should...

Aha, I have forgotten about that. My quick answer is, it should be used to reproduce the first version also. However, I need time to check if it reproduces very...

For the SPCV2/12, we used TFDS. https://www.tensorflow.org/datasets/catalog/speech_commands And we are sorry that we evaluated with old code, which is not compatible with the current code. Honestly, we need to rewrite...

That's the problem. We totally relied on the TFDS metadata. No CSV... I am sorry that we cannot help with it. P.S. AFAIRC, it was not a matter only with...

@Huiimin5 Thank you for waiting. (Though I guess it's too late for your ICASSP submission) ### Quick answers - Is the [voxforge.csv](https://raw.githubusercontent.com/nttcslab/eval-audio-repr/main/evar/metadata/voxforge.csv) compatible with the first version of BYOL-A? No....

@Huiimin5 Hi, I'm closing this issue. But you can re-open whatever you wish to ask. Thanks for your questions.