Join Jonathan Fernandes for an in-depth discussion in this video What you should know before watching this course, part of Transfer Learning for Images Using PyTorch: Essential Training.
- [Instructor] This course is designed to introduce you to the power of transfer learning in PyTorch. So you'll need to have some basic Python background knowledge. Now if you've worked with another deep learning framework, that'll come in handy. If you're new to deep learning, it'll probably help to check out my PyTorch deep learning course. We're going to be using Google Colab for this course. It's great because you don't need to install anything and you can just run the notebooks from your browser. Google also gives you access to GPUs, or graphical processing units, for free, which we'll use for training our models. Now as we go through the steps to train a model, we'll take a look at how this is done behind the scenes. Now if some of the sections seem a little bit more involved and complicated, that's okay. You can always come back to that section later. If you follow along, you'll have a good overall grasp of what's happening under the hood.
- What is transfer learning?
- Using autograd
- Creating a fixed feature extractor
- Training an extractor
- Fine-tuning the ConvNet
- Learning rates and differential learning rates