https://github.com/abdo-reda/mynafnet
This is a repo for Image Denoising model
https://github.com/abdo-reda/mynafnet
Last synced: 8 months ago
JSON representation
This is a repo for Image Denoising model
- Host: GitHub
- URL: https://github.com/abdo-reda/mynafnet
- Owner: Abdo-reda
- License: other
- Created: 2022-11-09T18:00:53.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-12-05T17:45:55.000Z (over 3 years ago)
- Last Synced: 2024-12-18T06:33:53.361Z (over 1 year ago)
- Language: Python
- Size: 1.44 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: ReadMe.md
- License: LICENSE
Awesome Lists containing this project
README
# Deep Learning Project - Image Denosing - NafNet Model
## Inference
For Inference, please use the following [Notebook](https://colab.research.google.com/drive/1BjQfvzMe9aRvhlItpOCdoCet9XNBJvsE?usp=sharing)
## Training
### Download Dataset
##### Download the train set and place it in ```./datasets/SIDD/Data```:
* [google drive](https://drive.google.com/file/d/1UHjWZzLPGweA9ZczmV8lFSRcIxqiOVJw/view?usp=sharing)
* ```python scripts/data_preparation/sidd.py``` to crop the train image pairs to 512x512 patches and make the data into lmdb format.
##### Download the evaluation data (in lmdb format) and place it in ```./datasets/SIDD/val/```:
* [google drive](https://drive.google.com/file/d/1gZx_K2vmiHalRNOb1aj93KuUQ2guOlLp/view?usp=sharing) or [百度网盘](https://pan.baidu.com/s/1I9N5fDa4SNP0nuHEy6k-rw?pwd=59d7),
* it should be like ```./datasets/SIDD/val/input_crops.lmdb``` and ```./datasets/SIDD/val/gt_crops.lmdb``
### Setup Enviornment
python3 venv env
source env/bin/activate
pip3 install -r requirements_train.txt
#### List of Dependencies:
* addict
* future
* lmdb
* numpy
* opencv-python
* Pillow
* pyyaml
* requests
* scikit-image
* scipy
* tb-nightly
* tqdm
* yapf
* torch
* torchvision
### Train the Model
python -m torch.distributed.launch NAFNet/basicsr/train.py -opt NAFNet/options/train/SIDD/NAFNet-width32.yml --launcher pytorch
### Notes
- Make sure to download the correct version of torch for your system/gpu.
- Make sure to change the files that point to the dataset directory, (Options file.)