Last Updated on March 6, 2023
With the availability of huge amounts of data for research and powerful machines to run your code on with distributed cloud computing and parallelism across GPU cores, Deep Learning has helped to create self-driving cars, intelligent voice assistants, pioneer medical advancements, machine translation, and much more. Deep Learning has become an indispensable tool for countless industries.
This series looks at highly promising machine learning and deep learning software for Linux. We’ll cover a wide range of applications of this technology. The first article in the series looked at GFPGAN, deep learning software for real-world face restoration. Real-ESRGAN and GFPGAN have been integrated with each other, but they are also individual projects from the same developer. Real-ESRGAN is a project that aims to create practical algorithms for general image/video restoration as opposed to face restoration.
We tested this software on a fresh installation of Ubuntu 22.10. First, install git and pip.
$ sudo apt install git python3-pip
Next, clone the project’s GitHub repository with the command:
$ git clone https://github.com/xinntao/Real-ESRGAN.git
Change into the newly created directory:
$ cd Real-ESRGAN
$ pip install basicsr
$ pip install facexlib
$ pip install gfpgan
$ pip install -r requirements.txt
$ sudo python3 setup.py develop
If you find that installing basicsr stalls on metadata, we recommend installing the facexlib dependency first.
Next, you can either download an executable file (Linux, macOS and Windows are available) or use the Python inference_realesrgan.py script that’s already present in the GitHub repository.