PyNET-PyTorch
PyNET-PyTorch copied to clipboard
Training Bokeh Problem
In the project, " Compared to the original TensorFlow model, this implementation contains three major modifications: Instance normalization is used in PyNET's level 1. Transposed convolutional layers are replaced with upsampling convolution. Modified weight coefficients of the loss functions. "
So if I want train bokeh with ebb dataset, I need
- not used instance normalization in level ?
- upsampling convolution still used?
- what's weight coefficients of the loss functions? It just confused me !