How to use the top model HAT in the super resolution category

Use the top benchmark model

low resolution

high resolution by HAT

GitHub - XPixelGroup/HAT: CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer…

install

git clone https://github.com/XPixelGroup/HAT.git
cd HAT
pip install -r requirements.txt
python setup.py develop

Download pre-trained model

pip install — upgrade gdown
gdown https://drive.google.com/u/0/uc?id=1Ma12vCWT27P9M99-s2RXnynKN-OQsBrv

Pre-trained models provided in the repository can be found on Google Drive.

HAT_Pretrained_Models - Google Drive

Rewriting the configuration file

Below are the steps to run it with an image you have prepared yourself.

The configuration file for the model in options/test

path:
 pretrain_network_g: ./experiments/pretrained_models/Real_HAT_GAN_SRx4.pth

Replace with the path of the pre-trained model file you downloaded earlier.

dataset items

datasets:
  test_1:  # the 1st test dataset
    name: custom
    type: SingleImageDataset
    dataroot_lq: input_dir
    io_backend:
      type: disk

and specify the path of the directory containing the image you want to super-resolve in dataroot.

Set the val items to only the following.

val:
 save_img: true
 suffix: ~ # add suffix to saved images, if None, use exp name

execution

Run the test by specifying the configuration file rewritten above.

python hat/test.py -opt options/test/HAT_GAN_Real_SRx4.yml

Results are saved in the results directory.

Low resolution 644*799

High resolution 2576*3196

The background is now clear.

If you encounter CUDA out of memory, add the following to the configuration file.
Divide the input image into smaller pieces and execute.

tile: # use the tile mode for limited GPU memory when testing.
 tile_size: 512 # the higher, the more utilized GPU memory and the less performance change against the full image. must be an integer multiple of the window size.
 tile_pad: 32 # overlapping between adjacency patches.must be an integer multiple of the window size.

🐣

I’m a freelance engineer.
Work consultation
Please feel free to contact us with a brief development description.
rockyshikoku@gmail.com

I am creating applications using machine learning and AR technology.

I send machine learning / AR related information.

GitHub

Twitter
Medium