about the pretrained model
yuffon opened this issue · 1 comments
yuffon commented
The flow based model is very very interesting. But it is too GPU hungry.
I see that some pretrained models are uploaded.
Now I have a question about the pretrained model on CelebA.
For unoptimized model, the input for encoding includes three tensors:
'enc_x': 'input/image', 'enc_x_d': 'input/downsampled_image', 'enc_y': 'input/label'
I want to know the relationship between enc_x and enc_x_d.
If I want to test the model on 32x32 CelebA, how should I use this pretrained model?
isharifi commented
That's also my question.