In this part, we design and train two different neural network models for image the inpainting task. In short, inpainting is a process of filling in the missing parts of an image.
The link to dataset is MNIST
Using PyTorch is mandatory for this Code.
Note that this code needs a CUDA-enabled GPU to be able to train the models in a reasonable time. If you do not have one, it is suggested to use the Colab environment.