This is the code repository for Hands-On Deep Learning with Caffe2 [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
All classes in this course are hands-on; you will get sufficient background about each class's content, and you will then go through critical examples that you need to know. At the end of each to, you will also be presented with quizzes to help you master Caffe2.
- 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.
This course is intended for machine learning enthusiasts keen to learn the exciting new Caffe2 framework for training deep learning models. No prior knowledge of deep learning is expected, but some knowledge of linear algebra and machine learning is required.
This course has the following requirements:
Setup and Installation
This will vary on a product-by-product basis, but should be a standard PI element for ILT products. This example is relatively basic.
Minimum Hardware Requirements
For successful completion of this course, students will require the computer systems with at least the following:
- OS: Ubuntu 14.04 or above; alternative, Mac OSX 10.12 or above
- Processor: Intel Core i5 or equivalent
- Memory: 4GB RAM
- Storage: 35 GB available space
For an optimal experience with hands-on labs and other practical activities, we recommend the following configuration:
- OS: Ubuntu 16.04 or equivalent; alternative, Mac OSX 10.13 or equivalent
- Processor: Intel Core i5 or equivalent
- Memory: 8GB RAM
- Storage: 35 GB available space
- Graphics card: Nvidia GTX 1060 or above (Not required if you can use the AWS GPU instance g3, p2, p3, etc. Google Cloud GPU computing engine instance)
Software Requirements
- OS: Ubuntu 14.04; Mac OSX 10.12
- Browser: Google Chrome / FireFox
- Code Editor: Atom: https://atom.io/
- Others: MiniConda 2/3: https://conda.io/miniconda.html