PyTorch-GAN
PyTorch-GAN copied to clipboard
eriklindernoren
PyTorch implementations of Generative Adversarial Networks.
Hello, I have one doubt. I am using my custom dataset for implementing cycle Gans. I have preprocessed my image data sets and extracted patches as I want to send...
已经解决了win10下的训练自己的数据问题，加Q群857449786 注明GAN 共同研究
I notice that the generated images have higher brightness and more colors than the original image, or the resulting images of other approaches. What causes it?
Hello there, First of all thanks for your amazing work on gans. you made them really easy to understand for newbies. I added a few things to gan.py and cgan.py...
I am trying to implement The LSTM conditional GAN architecture from this paper [Generating Image Sequence From Description with LSTM Conditional GAN](https://arxiv.org/pdf/1806.03027) to generate the handwritten data. The main architecture...
pix2pix is not an unpaired method. The paper title of pix2pix in README.md is wrong. I guess this may mislead someone.
According the original implementation, the kernel_size of nn.AvgPool2d is 3.
I noticed that the discriminator does not have activation function in the output. The last layer is just a convolution. Why is that?
torch.nn.CrossEntropyLoss() does not need softmax activation.
Metadata
Owner
Metadata
PyTorch implementations of Generative Adversarial Networks.