Dayoung, Baik

 I used skip.py for model. channel = [32,64,128] but there is no skip connection in 32 channels...

I got errors in load_state_dict in IRCNN

1

 I downloaded icrnn gray pth and loaded to model ircnn but it didn't work. How can I solve it? (What I erased is my private information)

I have ipynb that you had made based on pytorch cnn but it is now deleted from your github Is there any problem with pytorch cnn? I have had diffculty...

I am going through your MaskGIT code to study how to implement it, Thank you! But I have a question about VQGAN for tokenization. I think VQGAN for tokenization and...

` self.target_frame_inds = np.arange(2, len(self.spectrogram) // self.audio.num_bins_per_frame - 2) ` In voxtest_dataset.py L107, target frame index starts from 2. But in the paper, it starts from 1 (it means start...

The author Hangz answered other's question about training code. He answered that losses or differenct modules for training are available on av_models.py. But is there any difference b.t.w training and...

You set batchsize differently in parser arg and ds_config.json. For example, in cifar, in ds_config.json, train_batch_size is 16 but in parser argument, batchsize is 32. But you set batchsize as...

 I got an error like this... It seems like not my docker problem but in your code...So I want you to check it! I guess there has been no...

 I think _ext.cpython-37m-x86_64-linux-gnu.so file causes this problem. But I can not open it....

I want to use frame-level ssast just for frame-level audio token extraction

3

 in your ast_models.py, you put cluster True as Default  But if to use frame-level ssast, cluster should be False. Do I have to turn it off?  If...