Vision Projects using PyTorch

This repository has PyTorch tutorials on:

Image Classification

• MNIST Playbook : We train a network that is build from scratch in PyTorch and use tensorboard toolkit to visualise the results. In the end, I also show how we perform FGSM attack (adversial example) on this trained model.
• STN : Spatial Transformer Networks allow a neural network to learn how to perform spatial transformations on the input image in order to enhance the geometric invariance of the model.
• LeNet : Implementation of LeNet network on MNIST dataset.
• AlexNet : Implementation of AlexNet architecture, that won ImageNet challenge in 2012. In this notebook we have used Tensorboard for visualizations and CIFAR10 as the training dataset.
• VGG16: Implementation of 2014 ImageNet Challenge winner. In this notebook, we look at the concept of transfer learning.

Object Detection

TODO

Semantic Segmentation

TODO

Instance Segmentation

TODO