https://github.com/elifgokpinar/deepfillv2-test-images-guide

Test stages of Gated Convolution (DeepFillv2) inpainting method is explained.
https://github.com/elifgokpinar/deepfillv2-test-images-guide

deepfillv2 gated-convolution inpainting python test

Last synced: about 2 months ago
JSON representation

Test stages of Gated Convolution (DeepFillv2) inpainting method is explained.

• Host: GitHub
• URL: https://github.com/elifgokpinar/deepfillv2-test-images-guide
• Owner: elifgokpinar
• Created: 2022-04-06T08:29:21.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2023-07-22T10:18:37.000Z (over 1 year ago)
• Last Synced: 2023-07-22T10:26:48.742Z (over 1 year ago)
• Topics: deepfillv2, gated-convolution, inpainting, python, test
• Language: Python
• Homepage:
• Size: 537 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# DeepFillv2 Test Images Guide

Test stages of Gated Convolution (DeepFillv2) inpainting method are explained.

 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/18C2dZjzv7ap_2WVtJUp2ZXfIdP2Jq8u2?usp=sharing)

 

Requirements



  
Install python3.

  
Install tensorflow (tested on Release 1.3.0, 1.4.0, 1.5.0, 1.6.0, 1.7.0).



I used Python 3.7, Tensorflow 1.15, CUDA 10


Test Stages



  
Install software requirements

  
Clone the deepfillv2 github project on your computer = git clone https://github.com/JiahuiYu/generative_inpainting



  
Install tensorflow toolkit neuralgym (run pip install git+https://github.com/JiahuiYu/neuralgym)

  
Generate masked images (link). I used NVIDIA Irregular Mask Dataset: Testing Set.



  
Generate test commands file  (link). (The system takes 2 inputs to test : masked image and mask image. Pay attention the masked image and mask image paths while generating test command file.)

  
Run the commands file in your computer.



Examples


![masked_image_9](https://user-images.githubusercontent.com/72789565/164889078-d2cd42cc-7d0f-4242-bf0d-7945684ba018.png) ![9](https://user-images.githubusercontent.com/72789565/164889111-12275eb9-dbc3-47ce-8f40-a5f595428a63.png) ![00008](https://user-images.githubusercontent.com/72789565/164889148-56e87c38-7624-4465-ba5a-d50481601d6c.png)

![masked_image_6](https://user-images.githubusercontent.com/72789565/164889315-9eb7f384-980f-47a6-9152-c95775c5b970.png)

 ![6](https://user-images.githubusercontent.com/72789565/164889285-de209c5b-1f08-410b-bdde-8a3577a7ef58.png)

 ![00005](https://user-images.githubusercontent.com/72789565/164889274-fa781ab0-a7a0-4363-b073-949f03686c05.png)

From celeba_hq dataset. First column shows masked image, second column shows mask image and third column shows inpainting result.

## Citing

```

@article{yu2018generative,

  title={Generative Image Inpainting with Contextual Attention},

  author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},

  journal={arXiv preprint arXiv:1801.07892},

  year={2018}

}

@article{yu2018free,

  title={Free-Form Image Inpainting with Gated Convolution},

  author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},

  journal={arXiv preprint arXiv:1806.03589},

  year={2018}

}

```