ART
PyTorch code for our ICLR 2023 paper "Accurate Image Restoration with Attention Retractable Transformer".
File Explorer
Download Latest Version (.zip)- __init__.py
- arch_util.py
- art_arch.py
- artunet_arch.py
- __init__.py
- data_sampler.py
- data_util.py
- paired_image_dataset.py
- prefetch_dataloader.py
- single_image_dataset.py
- transforms.py
- __init__.py
- loss_util.py
- losses.py
- __init__.py
- metric_util.py
- psnr_ssim.py
- __init__.py
- art_model.py
- base_model.py
- lr_scheduler.py
- sr_model.py
- __init__.py
- dist_util.py
- file_client.py
- img_util.py
- logger.py
- matlab_functions.py
- misc.py
- options.py
- registry.py
- __init__.py
- test.py
- train.py
- version.py
- example.png
- README.md
- README.md
- CAR.png
- ColorDN.png
- ComS_img_092_ART_x4.png
- ComS_img_092_Bicubic_x4.png
- ComS_img_092_HR_x4.png
- ComS_img_092_SwinIR_x4.png
- ComS_img_098_ART_x4.png
- ComS_img_098_Bicubic_x4.png
- ComS_img_098_HR_x4.png
- ComS_img_098_SwinIR_x4.png
- git.png
- RealDN.png
- Resize_ComL_img_092_HR_x4.png
- Resize_ComL_img_098_HR_x4.png
- SR.png
- Visual_DN.png
- Visual_SR_1.png
- Visual_SR_2.png
- test_ART_SR_x2_without_groundTruth.yml
- test_ART_SR_x3_without_groundTruth.yml
- test_ART_SR_x4_without_groundTruth.yml
- test_ART_CAR_q10.yml
- test_ART_CAR_q30.yml
- test_ART_CAR_q40.yml
- test_ART_ColorDN_level15.yml
- test_ART_ColorDN_level25.yml
- test_ART_ColorDN_level50.yml
- test_ART_S_SR_x2.yml
- test_ART_S_SR_x3.yml
- test_ART_S_SR_x4.yml
- test_ART_SR_x2.yml
- test_ART_SR_x3.yml
- test_ART_SR_x4.yml
- train_ART_CAR_q10.yml
- train_ART_CAR_q30.yml
- train_ART_CAR_q40.yml
- train_ART_ColorDN_level15.yml
- train_ART_ColorDN_level25.yml
- train_ART_ColorDN_level50.yml
- train_ART_S_SR_x2.yml
- train_ART_S_SR_x3.yml
- train_ART_S_SR_x4.yml
- train_ART_SR_x2.yml
- train_ART_SR_x3.yml
- train_ART_SR_x4.yml
- meta_info_DIV2K800sub_GT.txt
- meta_info_REDS4_test_GT.txt
- meta_info_REDS_GT.txt
- meta_info_REDSofficial4_test_GT.txt
- meta_info_REDSval_official_test_GT.txt
- meta_info_Vimeo90K_test_fast_GT.txt
- meta_info_Vimeo90K_test_GT.txt
- meta_info_Vimeo90K_test_medium_GT.txt
- meta_info_Vimeo90K_test_slow_GT.txt
- meta_info_Vimeo90K_train_GT.txt
- __init__.py
- data_sampler.py
- data_util.py
- ffhq_dataset.py
- paired_image_dataset.py
- prefetch_dataloader.py
- reds_dataset.py
- single_image_dataset.py
- transforms.py
- video_test_dataset.py
- vimeo90k_dataset.py
- __init__.py
- fid.py
- metric_util.py
- niqe.py
- niqe_pris_params.npz
- psnr_ssim.py
- __init__.py
- arch_util.py
- artunet_arch.py
- __init__.py
- loss_util.py
- losses.py
- __init__.py
- base_model.py
- image_restoration_model.py
- lr_scheduler.py
- __init__.cpython-38.pyc
- __init__.py
- bundle_submissions.py
- create_lmdb.py
- dist_util.py
- download_util.py
- face_util.py
- file_client.py
- flow_util.py
- img_util.py
- lmdb_util.py
- logger.py
- matlab_functions.py
- misc.py
- options.py
- test.py
- train.py
- version.py
- train_ART_RealDN.yml
- evaluate_sidd.m
- README.md
- setup.cfg
- setup.py
- test_real_denoising_dnd.py
- test_real_denoising_sidd.py
- utils.py
- VERSION
- .gitignore
- LICENSE
- README.md
- requirements.txt
- setup.py
- VERSION
# Installation Guide
1. Get the code
git clone https://github.com/gladzhang/ART
Downloads the entire project code from GitHub to your computer.
cd ART
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
python -m torch.distributed.launch --nproc_per_node=4 --master_port=2414 basicsr/train.py -opt options/train/train_ART_SR_x2.yml --launcher pytorch
Runs the Python script (or module).
python -m torch.distributed.launch --nproc_per_node=4 --master_port=2414 basicsr/train.py -opt options/train/train_ART_SR_x3.yml --launcher pytorch
Runs the Python script (or module).
python -m torch.distributed.launch --nproc_per_node=4 --master_port=2414 basicsr/train.py -opt options/train/train_ART_SR_x4.yml --launcher pytorch
Runs the Python script (or module).
python -m torch.distributed.launch --nproc_per_node=4 --master_port=2414 basicsr/train.py -opt options/train/train_ART_S_SR_x2.yml --launcher pytorch
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)