willpyt98 / SRCNN_pytorch

An implementation of SRCNN using pytorch

SRCNN_pytorch

An implementation of SRCNN using pytorch The orignal paper is Image Super-Resolution Using Deep Convolutional Networks here

Difference from the original paper

1. Adam is used instead of SGD
2. Removed weight initialization
3. Trained on a different dataset. The dataset is available here: BaiduYun

Result

The result is better than bicubic to enlarge a 2x pic. Follow are the bicubic-img and srcnn-img

psnr of Bicuibic image = 26.492; psnr of SRCNN image = 28.687

Train

python train.py --output-dir './result' --optimizer Adam --num-epoch 50 --batch-size 128

Test

python test.py --image-file test/4.jpg --net-file result/Adam/final_net.pth