Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep-super-resolution

A fully custom Image Super-Resolution system built from scratch using Python, CuPy, and C++ acceleration, without relying on frameworks like PyTorch, TensorFlow, or JAX.

This project focuses on understanding deep learning at its core by implementing a Residual CNN for 2× image upscaling, complete with manual forward and backward propagation, GPU acceleration, and performance optimizations.

About

A fully custom Image Super-Resolution system built from scratch using Python, CuPy, and C++ acceleration without PyTorch or TensorFlow.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages