https://github.com/ajithvcoder/deblurganv2_customdataset

Using deblur GAN on custom dataset
https://github.com/ajithvcoder/deblurganv2_customdataset

custom-dataset deblurgan deblurring deep-learning gan generative-adversarial-network

Last synced: 24 days ago
JSON representation

Using deblur GAN on custom dataset

• Host: GitHub
• URL: https://github.com/ajithvcoder/deblurganv2_customdataset
• Owner: ajithvcoder
• License: other
• Created: 2023-05-07T08:29:36.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-05-07T10:40:03.000Z (almost 2 years ago)
• Last Synced: 2024-11-13T10:49:19.643Z (3 months ago)
• Topics: custom-dataset, deblurgan, deblurring, deep-learning, gan, generative-adversarial-network
• Language: Jupyter Notebook
• Homepage:
• Size: 16.4 MB
• Stars: 3
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Using deblurv2 GAN on custom dataset

**Dataset preparation**

You can download any set of images which are text, scenery etc . Using gaussian blur you can blur a copy of the images.

I have took  a dataset from [roboflow](https://universe.roboflow.com/yashwanthworkspace/numbers-identification) .

Made following folders 

```

--Licenseplate_blur_clear_dataset

    --train

        --blur

        --sharp

    --test

        --blur

        --sharp

    --valid

        --blur

        --sharp

```

Copy original images of train,test,valid to sharp folder. To fill the images in blur folder you can use [this code](./util/blur_image.py). now we are done with data preparation. Dataset which i prepared can be [found here](https://drive.google.com/file/d/1Mk99lU3zJgBkBpHTl0PigJ3UiSX4yyKB/view?usp=sharing)

**Installation**

```pip install -r requirements.txt```

**Train**

```python train.py```

**Test**

pretrained weights can be [found here](https://drive.google.com/file/d/1M0zk2udF6GfGgMI84xCcGrUmnyZGsg1T/view?usp=sharing)

```python predict.py -i ./test_img -o ./submit -m ./saved_models/best_fpn.h5``` 

**Gallery**

























**Colab Notebook**

[Notebook](https://colab.research.google.com/drive/1yHv9dZt_GYQW69RSbShhwR1TChauF9BL?usp=sharing)

**Credits**

- [DeblurGANv2](https://github.com/VITA-Group/DeblurGANv2)