Have you ever wanted to test multiple Deep Learning models and compare their results very easily?
Are you tired of picking a Deep Learning model just because it is the only one you are able to run?
We want to solve this problem and we packaged 1 state-of-the-art Super-Resolution Deep Learning models for you to easily test it.
We are calling this new way of packaging Deep Learning models: Rockets.
Welcome to the Rockets Scientists Community!!!
We recommend you to use an isolated Python environement such as virtualenv or conda with at least Python 3.6. Then you can use the following lines of code:
git clone https://github.com/LucasVandroux/PyTorch-Rocket-ESRGAN
cd PyTorch-Rocket-ESRGAN
pip install rocketbase
As the installation for PyTorch is different for each platform, you need to look at the PyTorch installation guide. Don't worry it is very simple, maximum 2 lines of codes 😝
For this tutorial, we selected the state-of-the-art model in Super-Resolution for you to play with. It means that now you are able to improve the resolution of your images in just a few line of codes:
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks [paper]
Everything is happening in the improve.py file. There you can choose which image to use with just one line of code.
Once you are ready you just need to run python improve.py and everything will happen magically.
Don't hesitate to play around by using different images with the ESRGAN Rocket. We recommend to use .png images instead of .jpg as the compression in the last one seems to decrease the quality of the improved image.
| Filename | Original | Improved |
|---|---|---|
girl1.png |
 |
 |
girl2.png |
 |
 |
lion.png |
 |
 |
Any feedback or complaint from your neighbors about the noise your Rockets are making, please contact us at hello@mirage.id.