GuideWsp/ClassSR

(CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

ClassSR

(CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

Paper

Authors: Xiangtao Kong, Hengyuan Zhao, Yu Qiao, Chao Dong

Dependencies

• Python >= 3.6 (Recommend to use Anaconda)
• PyTorch >= 1.5.0
• NVIDIA GPU + CUDA
• Python packages: pip install numpy opencv-python lmdb
• [option] Python packages: pip install tensorboardX, for visualizing curves.

Codes

• Our codes version based on BasicSR.

How to test a single branch

1. Clone this github repo.

git clone https://github.com/Xiangtaokong/ClassSR.git
cd ClassSR

2. Download the testing datasets (DIV2K_valid).

3. Download the divide_val.log and move it to .codes/data_scripts/.

4. Generate simple, medium, hard (class1, class2, class3) validation data.

cd codes/data_scripts
python extract_subimages_test.py
python divide_subimages_test.py

5. Download pretrained models and move them to ./experiments/pretrained_models/ folder.

6. Run testing for a single branch.

cd codes
python test.py -opt options/test/test_FSRCNN.yml
python test.py -opt options/test/test_CARN.yml
python test.py -opt options/test/test_SRResNet.yml
python test.py -opt options/test/test_RCAN.yml

7. The output results will be sorted in ./results.

How to test ClassSR

1. Clone this github repo.

git clone https://github.com/Xiangtaokong/ClassSR.git
cd ClassSR

2. Download the testing datasets (DIV8K). Test8K contains the images (index 1401-1500) from DIV8K. Test2K/4K contain the images (index 1201-1300/1301-1400) from DIV8K which are downsampled to 2K and 4K resolution.

3. Download pretrained models and move them to ./experiments/pretrained_models/ folder.

4. Run testing for ClassSR.

cd codes
python test_ClassSR.py -opt options/test/test_ClassSR_FSRCNN.yml
python test_ClassSR.py -opt options/test/test_ClassSR_CARN.yml
python test_ClassSR.py -opt options/test/test_ClassSR_SRResNet.yml
python test_ClassSR.py -opt options/test/test_ClassSR_RCAN.yml

5. The output results will be sorted in ./results.

How to train a single branch

1. Clone this github repo.

git clone https://github.com/Xiangtaokong/ClassSR.git
cd ClassSR

2. Download the training datasets(DIV2K) and validation dataset(Set5).

3. Download the divide_train.log and move it to .codes/data_scripts/.

4. Generate simple, medium, hard (class1, class2, class3) training data.

cd codes/data_scripts
python data_augmentation.py
python extract_subimages_train.py
python divide_subimages_train.py

5. Run training for a single branch (default branch1, the simplest branch).

cd codes
python train.py -opt options/train/train_FSRCNN.yml
python train.py -opt options/train/train_CARN.yml
python train.py -opt options/train/train_SRResNet.yml
python train.py -opt options/train/train_RCAN.yml

6. The experiments will be sorted in ./experiments.

How to train ClassSR

1. Clone this github repo.

git clone https://github.com/Xiangtaokong/ClassSR.git
cd ClassSR

2. Download the training datasets (DIV2K) and validation dataset(DIV2K_valid, index 801-810).

3. Generate training data (the all data(1.59M) in paper).

cd codes/data_scripts
python data_augmentation.py
python extract_subimages_ClassSR.py

4. Download pretrained models(pretrained branches) and move them to ./experiments/pretrained_models/ folder.

5. Run training for ClassSR.

cd codes
python train_ClassSR.py -opt options/train/train_ClassSR_FSRCNN.yml
python train_ClassSR.py -opt options/train/train_ClassSR_CARN.yml
python train_ClassSR.py -opt options/train/train_ClassSR_SRResNet.yml
python train_ClassSR.py -opt options/train/train_ClassSR_RCAN.yml

6. The experiments will be sorted in ./experiments.

Contact

Email: xt.kong@siat.ac.cn