https://github.com/pythonista7/dncnn-tf2
Using CNN to de noise images.
https://github.com/pythonista7/dncnn-tf2
denoising-images denoising-network dncnn gaussian-noise tf2
Last synced: 5 months ago
JSON representation
Using CNN to de noise images.
- Host: GitHub
- URL: https://github.com/pythonista7/dncnn-tf2
- Owner: Pythonista7
- Created: 2020-10-26T14:41:51.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2021-05-08T06:14:57.000Z (over 4 years ago)
- Last Synced: 2025-01-11T04:04:07.338Z (about 1 year ago)
- Topics: denoising-images, denoising-network, dncnn, gaussian-noise, tf2
- Language: Python
- Homepage:
- Size: 173 KB
- Stars: 5
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep Denoise
This is a tensorflow-2 implementation of the paper [Beyond a Gaussian Denoiser: Residual Learning ofDeep CNN for Image Denoising](https://arxiv.org/pdf/1608.03981.pdf).
### Dataset used :
[BSDS200](https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/BSDS300-images.tgz)
To download and unpack run:
`wget https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/BSDS300-images.tgz`
`tar -xvzf BSDS300-images.tgz`
### Requriments :
* tensorflow==2.3.1
* matplotlib
* numpy
### Run Model
Run train_denoise.py
### Results
After training by setting depth=5 for 25 epoch we get the below results. The original paper suggests a deeper architecture feel free to tweak the hyper params in the [train_denoise.py](train_denoise.py) file.
