synthetica3d

Results 2 comments of synthetica3d

exporting the pix2pix model to onnx model, but the inference result by onnx is incorrect

If you train with --norm instance the problem should go away. I noticed that if you run the test program after calling eval() on netG, the result will also be...

256 pixel output, not 512, despite training on --load_size 512

How about that --crop size 256? Doesn't sound like what you want.