Reshaping the latent feature at the end of Discriminator - Githubissues

daniel-merrick / Learning-from-Simulated-and-Unsupervised-Images-through-Adversarial-Training-SimGAN-PyTorch

PyTorch implementation of 'Learning from Simulated and Unsupervised Images through Adversarial Training'

14 stars 2 forks source link

Reshaping the latent feature at the end of Discriminator #1

Open koutilya-pnvr opened 5 years ago

koutilya-pnvr commented 5 years ago

https://github.com/dmerrick520/Learning-from-Simulated-and-Unsupervised-Images-through-Adversarial-Training-SimGAN-PyTorch/blob/e70fbb89e11896a112eb4ff854dabcf73d597413/simgan/lib/simgan_network.py#L111

Why not just output = convs.view(-1,2) ?? Is it really required to permute before reshaping?