PyTorch implementation of Image-to-Image Translation Using Conditional Adversarial Networks.
Based on pix2pix by Isola et al.
The examples from the paper:
- Linux
- Python with numpy
- NVIDIA GPU + CUDA 8.0 + CuDNNv5.1
- pytorch
- torchvision
-
Clone this repo:
git clone https://gitlab.com/mlvc_lab/Pix2pix_base.git
cd Pix2pix_base
-
Get dataset
unzip dataset/facades.zip
-
Train the model:
python train.py --dataset facades --nEpochs 200 --cuda
-
Test the model:
python test.py --dataset facades --model checkpoint/facades/netG_model_epoch_200.pth --cuda