Would it be possible to choose Upsample and Downsample strategies? #13

Looking at the official BigGAN implementation in Tensorflow, I found they use ConvTranspose2d for Upsample and Conv2d for Downsample in the ResNet block (e.g. https://github.com/taki0112/BigGAN-Tensorflow/blob/master/ops.py#L159).

I know that BigGAN implementations in PyTorch use a combination of Pooling and Conv (e.q. https://github.com/ajbrock/BigGAN-PyTorch/blob/master/BigGAN.py#L341), but in my experience, I can't say for sure which is the better performance.

In the future, is it possible to flexibly select an operation to change the resolution of the input feature map?