ariss95/image_reconstructon_examples

image reconstruction with pytorch

image reconstruction

this repository contains two examples of reconstructing input images/videos with deep learning methods using pyTorch.

Auto Encoder

A simple auto encoder as described here:

it maps the images into the code, and then maps the code to the reconstructed images.

examples

Input images are on the first row.

dataset: MNIST

RNN

a simple, stacked Reccurent Neural Network model from pyTorch with ReLU activation function.

pytorch.org/docs/stable/generated/torch.nn.RNN.html

the loss function (mean square error) is minimized using Adam optimization.

examples

dataset: moving MNIST

data_loader.py

This script contains a class for easy loading of data from the moving MNIST dataset.

The dataset is splitted in training-validation and testing subsets. The training set is being shuffled after loading all data from it.

plot_utils.py

code for displaying images using matplotlib

For every method, the properties of the model are in the file model_"method name".py and the rest under the train_"method name".py