From the course: Computer Vision for Data Scientists
Join today to access over 24,900 courses taught by industry experts.
Setting up the environment
From the course: Computer Vision for Data Scientists
Setting up the environment
- [Instructor] I'm now going to give you a crash course in PyTorch. PyTorch is currently the most popular way to train deep learning models. And in this tutorial, I'm going to introduce you to PyTorch and how to use pre-trained models for image classification. You are going to use a ResNet-50 model pre-trained on ImageNet and then fine tune that model on the MiniPlaces dataset. I'm going to teach you about datasets, data loaders, loss functions, optimizers, data augmentation, and the training loop. This is a bare bones introduction to using PyTorch but it should get you familiar with the core concepts. Let's get into it. The first thing is setting up the environment. So you need to install PyTorch and TorchVision which are the libraries that we're going to use in this tutorial. You can simply install these using pip. But since we're using Google Colab, these are going to be already installed in the environment. Next is…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.