Haoran Zhou comments

Results 61 comments of


                                            Haoran Zhou

Both 'audio_rd'and 'val_audio_rd' ,'is_val' para set to 'False'?

yep

TypeError: Expected int32, got list containing Tensors of type '_Message' instead

I guess it's due to different tensorflow versions but I am not quite sure and don't have enough spare time to check the problem you have, sorry.

TypeError: Expected int32, got list containing Tensors of type '_Message' instead

I used tf r 0.11 at that time, I guess maybe 0.12 will also work fine(but I am not sure).

where is the model model.ckpt-1760000

I didn't upload my model and you can design your own speech data set and noise data set and use them for training.

Weights for trained model

I tried to upload some weights for test, but it says remote: error: File model.ckpt-492000 is 121.55 MB; this exceeds GitHub's file size limit of 100.00 MB To https://github.com/zhr1201/deep-clustering.git Sorry...

Weights for trained model

@pli1988 Guess you are studying at NYU? I'm currently applying for a PhD and it seems really hard...

how can i fix the following errors? -- audio_test.py

The error is due to your version of numpy doesn't allow casting the type from complex number(the output of the IFFT) to float64(the time domain signal). Actually the output of...

how can i fix the following errors? -- audio_test.py

You can check the values of the output audio data array to see if it is legit. If not, probably sth. in the model went wrong. If it is legit,...

Question about cluster permutation

Glad to know you like the rep! ( cor[1] > cor[0]) is not from the original paper. it is an intuitive move which might fail in some examples. I assume...

Folder 'dcdata'

Sorry for the misunderstanding, I meant train.py should be used to generate 1.pkl, 2.pkl...