Why flip weight and add 1 to bias when loading tensorflow pretrained model

[zengxianyu]

Thanks to the great work. I noticed that when loading the tensorflow pretrained model you flip "Conv0_up.conv.weight" and add 1 to the "conv.modulation.bias. Is this because of the difference between this implementation and the official one and maybe cause the performance drop?

[rosinality]

The approach of official implementations is slightly different from this repository. I choosed to initialize bias 1, official implementation uses bias initialized 0 and use + 1 for applying biases. And flipped convolution weights. But as these weights are all learnable, it should be equivalent between implementations.