Lorna
The implementation of CIFAR in the original ResNet paper is reproduced in my repository, please see (https://github.com/Lornatang/ResNet-PyTorch/tree/master/examples/cifar) Thank you, please give me some suggestions. @AmigoCDT
OK, you need to modify two places. 1- Change `config.py` 31 line `upscale_factor = 4` to **`upscale_factor = 2`** 2- Change `model.py` 139 line `for _ in range(2):` to **`for...
So, `inferernce.py` should use X4 model weights, if you use X2 model weights, maybe it is bad~ I'm talking about the case of using the pretrained model directly ^.^
This library gives X4 times the model, which cannot be directly used for X2 inference, you can try to load some model weights
You can refer to my implementation details for GAN in this repository(https://github.com/Lornatang/Generative-Adversarial-Network)。 @rajarajanvakil
You can refer to the implementation details for DCGAN in my repository(https://github.com/Lornatang/Deep-Convolutional-Generative-Adversarial-Network)。 @githubcyy
@JasonWong97 @VladAndronik I've tried to make some changes to this code and it works. In the near future, I will present my pre training model.See https://github.com/Lornatang/UGATIT-PyTorch
@GuoQuanhao PyTorch Version==1.5.
@PraetorP Without setting `light` to `True`, the model requires about 14G of running memory.