Gregory Johnson

main_loop.model.set_parameter_values(oldmodel.get_param_values()) needs to be main_loop.model.set_parameter_values(oldmodel.get_parameter_values())

3D SSIM

1

Or even N-dimensional SSIM!

Possible error of relativistic gan

2

in https://github.com/eriklindernoren/PyTorch-GAN/blob/master/implementations/relativistic_gan/relativistic_gan.py ``` if opt.rel_avg_gan: g_loss = adversarial_loss(fake_pred - real_pred.mean(0, keepdim=True), valid) else: g_loss = adversarial_loss(fake_pred - real_pred, valid) # Loss measures generator's ability to fool the discriminator g_loss =...

Flip dimension

1

Saw this great tool featured at Bioimage Informatics this week. It would be great if there were an option to choose which dimensions are viewed (i.e. x, y, t).

Specifically address https://github.com/AllenCellModeling/pytorch_fnet/pull/109#discussion_r275568478

i.e. separate argparse from main train loop to be able to specify "trainer" objects.