README

diff
+ Update July: Added support for action recognition and tracking
+              in the new release v1.2.


 Computer Vision

In recent years, we've see an extra-ordinary growth in Computer Vision, with applications in face recognition, image understanding, search, drones, mapping, semi-autonomous and autonomous vehicles. A key part to many of these applications are visual recognition tasks such as image classification, object detection and image similarity.

This repository provides examples and best practice guidelines for building computer vision systems. The goal of this repository is to build a comprehensive set of tools and examples that leverage recent advances in Computer Vision algorithms, neural architectures, and operationalizing such systems. Rather than creating implementations from scratch, we draw from existing state-of-the-art libraries and build additional utility around loading image data, optimizing and evaluating models, and scaling up to the cloud. In addition, having worked in this space for many years, we aim to answer common questions, point out frequently observed pitfalls, and show how to use the cloud for training and deployment.

We hope that these examples and utilities can significantly reduce the “time to market” by simplifying the experience from defining the business problem to development of solution by orders of magnitude. In addition, the example notebooks would serve as guidelines and showcase best practices and usage of the tools in a wide variety of languages.

These examples are provided as Jupyter notebooks and common utility functions. All examples use PyTorch as the underlying deep learning library.

 Examples

This repository supports various Computer Vision scenarios which either operate on a single image:

  


As well as scenarios such as action recognition which take a video sequence as input:

  



 Target Audience

Our target audience for this repository includes data scientists and machine learning engineers with varying levels of Computer Vision knowledge as our content is source-only and targets custom machine learning modelling. The utilities and examples provided are intended to be solution accelerators for real-world vision problems.

 Getting Started

To get started, navigate to the Setup Guide, which lists
instructions on how to setup the compute environment and dependencies needed to run the
notebooks in this repo. Once your environment is setup, navigate to the
Scenarios folder and start exploring the notebooks. We recommend to start with the image classification notebooks, since this introduces concepts which are also used by the other scenarios (e.g. pre-training on ImageNet).

Alternatively, we support Binder

which makes it easy to try one of our notebooks in a web-browser simply by following this link. However, Binder is free, and as a result only comes with limited CPU compute power and without GPU support. Expect the notebook to run very slowly (this is somewhat improved by r