guminov/learn_computer_vision

A repository created with the purpose of teaching students in BME lab 308A- Hanoi University of Science and Technology

learn_computer_vision

An organized collection of tutorials and projects created for aspriring computer vision students.

Getting started

To start learning computer vision, you should start by installing:

• Ubuntu (preferable 18 or over)
• Anaconda (for virtual environment)
• For computers with compatible NVIDIA GPU: Graphics cards drivers, CUDA and CUDNN.

Table of contents

• PyTorch Tutorials
• Assignments

PyTorch_Tutorials

Basics

• Tensor Basics
• Feedforward Neural Net
• Convolutional Neural Net
• Weight Load/Save
• Custom dataset
• Finetune / Transfer learning
• Augmentation using torchvision
• Albumentation
• Tensorboard

Architecture

• Classification with Resnet

Image_Segmentation

• Unet Image Segmenation

Object_Detection

• Object Detection with SSD

Assignments

Pytorch Assignments

• EX 1 - Building VGG-16
• EX 2 - Training Resnet-50 on CIFAR-10