- Install Caffe2 and prepare your developing environment.
- The basic elements of Caffe2—such as blobs^ workspaces^ and tensors—and how to use them to build a computational graph.
- Foundational knowledge about training models using Caffe2.
- The brew^ an API for creating models in Caffe2.
- Address the supervised learning problem of image classification using Caffe2.
- How to use RNNs in Caffe2 to learn to write poems like Shakespeare.
- Deep Q Network^ and how to use it in Caffe2.
- Running models on devices with Caffe2.
Caffe2^ open-sourced by Facebook^ is a simple^ flexible framework for efficient deep learning. This course will teach you about Caffe2 and show you how to train your deep learning models.
The course starts off with the basics of Caffe2 such as blobs^ workspaces^ operators^ and nets, moving on^ you will learn how to build a model using Caffe2 s new API brew. You will also learn how to create Convolutional Neural Networks (CNNs) that can identify not only handwriting but also fashion items from an image. You will work on transferring learning to allow you to work with CNN s for image recognition by fine-tuning models that are already pre-trained on a large-scale dataset. We cover common models such as ResNet-50. Finally^ the course will show you how to deploy your models on any platform.
By the end of this course^ you will be able to effectively train Deep Learning models with Caffe2^ providing you with high-performance and first-class support for large-scale distributed training^ mobile deployment^ new hardware support^ and flexibility.
About the Author
Shuai Zheng^ also known as Kyle^ did his Ph.D. degree in Machine Learning and Computer Vision at the University of Oxford. He has published in top-tier machine learning and computer vision conferences such as CVPR^ ECCV^ and ICCV. His research interests are in deep learning and its applications in computer vision such as semantic segmentation. He is currently a research scientist at eBay Inc^ where he works on both fundamental and practical problems in Augmented Reality^ Computer Vision^ and Deep Learning.