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 implementions 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.

Top collections

Don't forget to tag @Microsoft in your comment.

Authors community post
Open source, from Microsoft with love
Share this project
Similar projects
STEFANN: Scene Text Editor using Font Adaptive Neural Network
A generalized method for realistic modification of textual content present in a scene image. ⭐️ Accepted in CVPR 2020.
VirTex: Learning Visual Representations from Textual Annotations
We train CNN+Transformer from scratch from COCO, transfer the CNN to 6 downstream vision tasks, and exceed ImageNet features despite using 10x fewer ...
A Tensorflow-based framework to ease the training of generative models
The Illustrated FixMatch for Semi-Supervised Learning
Learn how to leverage unlabeled data using FixMatch for semi-supervised learning