Dataset Size for Training

auspicious3000 / autovc

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

https://arxiv.org/abs/1905.05879

MIT License

983 stars 207 forks source link

Dataset Size for Training #32

Closed jacob-mink closed 4 years ago

jacob-mink commented 4 years ago

I have seen in #27 that 300k steps is necessary for training. Do the original results use the entirety of the VCTK dataset with 9/10 train, 1/10 test as in the paper, or do they use only a subset of the VCTK dataset?

Also, just to clarify, a step or iteration is one batch being passed through the network, correct? i.e. If the dataset is of size 10000, then you get 5000 steps (or iterations) out of it on a batch size of 2 in one epoch.

auspicious3000 commented 4 years ago

The only use a subset.

Yes.

jacob-mink commented 4 years ago

The Chou et. al. set?