4.[Inpainting](Inpainting) refers to a conservation process where damaged, deteriorating, or missing parts of an artwork are filled in to present a complete image. Here, we specifically focus on filling the missing parts of the image. We use a subset of [ImageNet](http://www.image-net.org/) dataset to train our network. Every image inputed would be keep two version: the original version and a masked version. Masked images is created by adding a white mask to the center of the image. The task of generator is to fill these white areas to inpaint the image. The following image is a example of inpainting output. From top to bottom is masked image, inpainted image, original image


#### Reference
1.[Generative Adversarial Networks: Build Your First Models](https://realpython.com/generative-adversarial-networks/#your-first-gan)