Caffe2: Getting Started

Course Overview
Hi. My name is Janani Ravi, and welcome to this course on Caffe2: Getting Started. A little about myself. I have a Master's degree in Electrical Engineering from Stanford and have worked at companies such as Microsoft, Google, and Flipkart. At Google, I was one of the first engineers working on real-time collaborative editing in Google Docs, and I hold four patents for the its underlying technologies. I currently work on my own startup, Loonycorn, a studio for high-quality video content. In this course, you will learn the fundamentals of building neural nets and working with Caffe2, get introduced to the Caffe2 model zoo, and see how you can import models from PyTorch to Caffe2 using ONNX. We start off by understanding the basic building blocks of Caffe2: blobs, workspaces, nets, and operators. We'll put these together to build neural networks to perform tasks such as regression and classification. We'll then get introduced to common image preprocessing techniques and the Caffe2 model zoo, which offers a wide variety of pre-trained models for common use cases. We'll work with the SqueezeNet model for image classification. We'll then focus on interoperability between the PyTorch deep learning framework and Caffe2 using ONNX, an open-source framework for exporting models from one framework to another. We'll use ONNX to move a super-resolution model from PyTorch to Caffe2. At the end of this course, you should be comfortable building and executing neural networks using Caffe2, using the pre-trained models for common tasks, and using ONNX to move from one framework to another.