Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/andreimoraru123/super-resolution
Modern Graph TensorFlow implementation of Super-Resolution GAN
https://github.com/andreimoraru123/super-resolution
computer-vision gan generative-adversarial-network graph-mode high-resolution image-generation keras microsoft-coco peak-signal-to-noise-ratio photo-realistic-super-resolution pixelshuffle resnet structural-similarity sub-pixel subpixel-convolution super-resolution tensorflow tensorflow-applications vgg19 xla
Last synced: 9 days ago
JSON representation
Modern Graph TensorFlow implementation of Super-Resolution GAN
- Host: GitHub
- URL: https://github.com/andreimoraru123/super-resolution
- Owner: AndreiMoraru123
- Created: 2023-07-19T23:47:30.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-08-04T17:53:30.000Z (over 1 year ago)
- Last Synced: 2025-01-10T17:50:51.771Z (16 days ago)
- Topics: computer-vision, gan, generative-adversarial-network, graph-mode, high-resolution, image-generation, keras, microsoft-coco, peak-signal-to-noise-ratio, photo-realistic-super-resolution, pixelshuffle, resnet, structural-similarity, sub-pixel, subpixel-convolution, super-resolution, tensorflow, tensorflow-applications, vgg19, xla
- Language: Python
- Homepage:
- Size: 54.7 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Photo-Realistic Single Image Super-Resolution GAN
  
[](https://github.com/psf/black) [](https://mypy-lang.org/) [](https://github.com/AndreiMoraru123/Super-Resolution/actions/workflows/python-app.yml)
> [!NOTE]\
> I adapted the code from [this awesome PyTorch version](https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Super-Resolution). Please check it out as well.
> [!IMPORTANT]\
> I am using python `3.11` with tensorflow `2.12` on WSL2.
## Steps
1. `pip install -r requirements.txt`
2. download the [COCO dataset](https://cocodataset.org/#home) (I use COCO 2017).
3. download the [Set5, Set14, BSD100 test datasets](https://github.com/XPixelGroup/BasicSR/blob/master/docs/DatasetPreparation.md#common-image-sr-datasets)
4. [create_data_lists.py](https://github.com/AndreiMoraru123/Super-Resolution/blob/main/create_data_lists.py) creates the JSON files for training and testing from the COCO image paths.
5. [architecture.py](https://github.com/AndreiMoraru123/Super-Resolution/blob/main/architecture.py) defines the training blueprints for both models (ResNet and GAN).
6. [train.py](https://github.com/AndreiMoraru123/Super-Resolution/blob/main/train.py) runs the whole training pipeline with top-down logic found in the file. Everything is managed by the `Trainer` from [trainer.py](https://github.com/AndreiMoraru123/Super-Resolution/blob/main/trainer.py).
7. [resolve.py](https://github.com/AndreiMoraru123/Super-Resolution/blob/main/resolve.py) generates the super resolution images from a given high resolution image (the low resolution version to be solved is generated by down-sampling the given image) and evaluates the models using with `scikit-image`'s `peak_signal_noise_ratio` and `structural_similarity` using the `Evaluator` from [evaluator.py](https://github.com/AndreiMoraru123/Super-Resolution/blob/main/evaluator.py).
The code itself is heavily commented and you can get a feel for super-resolution models by looking at the [tests](https://github.com/AndreiMoraru123/Neural-Machine-Translation/tree/main/test).
## Overfitting on one image
- **Top-Left**: Bicubic Up-sampling
- **Top-Right**: Super Resolution ResNet
- **Bottom-Left**: Super Resolution GAN
- **Bottom-Right**: Original High Resolution
```
Evaluation results:
{ 'PSNR (SRGAN)': 29.44381,
'PSNR (SRResNet)': 29.380556,
'SSIM (SRGAN)': 0.87486875,
'SSIM (SRResNet)': 0.87476}
```