Linh Vu
Hi, Thanks for your detailed response. Regarding (1), my question was that Blending1() is not using LCC size, but how many neighbors have lower values than the center pixel: 0...
Seconded. Any updates on when training code is released?
Hi, VGGVox doesn't use MFCC, only FFT spectrum. The signal processing code is in `sigproc.py`.
Yes but if you look at the code of `mfccspec`, the return value `SPEC` is only FFT.
It's just weights. You'd probably want to export both weights and architecture before trying `keras_to_tensorflow`. Or replicate the model architecture in tf and restore weights from a dict.
Pretty sure I got the layer structure by following the Matlab model. Will check/update when I got more time.
Did this error pop up when you ran the sample config and data?
@zsdonghao I'd like to retrain. Where do I find `d_srgan.npz`? Thanks!
I'm experiencing a similar issue where calling `zero_to_fp32.py` after training a partially frozen model results in all frozen layers being dropped. While a workaround similar to @richarddwang's could work, this...