Pytorch is quickly gaining in popularity as a deep learning framework. If you have ever wondered, why bother with Pytorch when there are several other frameworks out there, then this is for you. This will be a hands-on tutorial quickly getting to speed with image classification using PyTorch, starting with the autograd function, CNN fundamentals and ending with the benefits of transfer learning.
In the first section we will create and work with tensors. We will look at working with gradients and Pytorch's autograd function. We will conclude this section with a simple regression problem to check our understanding of the fundamentals.
In the second section we will build an image classification model. We will have a whistle-stop tour of the fundamentals of CNNs including convolution layers, pooling layers and batch normalization. We will then create our demo classifier using the CIFAR-10 dataset.
In the final section we will use transfer learning - using a well known architecture as our starting point. We will have the chance to compare our previous results with transfer learning and compare and contrast the benefits of transfer learning. We will look at freezing layers for further training and improving the accuracy of the model.