This repository is implementation of the "Image Super-Resolution Using Deep Convolutional Networks".

• Added the zero-padding
• Used the Adam instead of the SGD
• Removed the weights initialization

• PyTorch 1.0.0
• Numpy 1.15.4
• Pillow 5.4.1
• h5py 2.8.0
• tqdm 4.30.0

The 91-image, Set5 dataset converted to HDF5 can be downloaded from the links below.

Otherwise, you can use prepare.py to create custom dataset.

python train.py --train-file "BLAH_BLAH/91-image_x3.h5" \
                --eval-file "BLAH_BLAH/Set5_x3.h5" \
                --outputs-dir "BLAH_BLAH/outputs" \
                --scale 3 \
                --lr 1e-4 \
                --batch-size 16 \
                --num-epochs 400 \
                --num-workers 8 \
                --seed 123                

Pre-trained weights can be downloaded from the links below.

The results are stored in the same path as the query image.

python test.py --weights-file "BLAH_BLAH/srcnn_x3.pth" \
               --image-file "data/butterfly_GT.bmp" \
               --scale 3

We used the network settings for experiments, i.e., .

PSNR was calculated on the Y channel.

Original	BICUBIC x3	SRCNN x3 (27.53 dB)
Original	BICUBIC x3	SRCNN x3 (29.30 dB)
Original	BICUBIC x3	SRCNN x3 (28.58 dB)