Reproduction of paper:Residual Dense Network for Image Super-Resolution
- python > 3.5
- tensorflow > 1.0
- scipy
- numpy
- pillow
- scipy
- tqdm
Download DIV2K training data.DIV2K
run sh run_train.sh
#!/usr/bin/env bash
CUDA_VISIBLE_DEVICES=0 python3 train.py \
--dataset data/DIV2K \
--imgsize 128 \
--scale 4 \
--globallayers 16 \
--locallayers 8 \
--featuresize 64 \
--batchsize 10 \
--savedir saved_models \
--iterations 1000 \
--usepre 0
python3 test.py --dataset [image dir]
or
python3 test.py --image [single image path]
Figure 1. The architecture of residual dense network (RDN).
Figure 2. Residual dense block (RDB) architecture.