A playbook for systematically maximizing the performance of deep learning models.

Differentiable convex optimization layers

An end-to-end PyTorch framework for image and video classification

A C++ standalone library for machine learning

Caffe2 is a lightweight, modular, and scalable deep learning framework.

Implements a message passing interface (MPI) wrapper that makes it easy to do massively parallel computations inside the Torch deep-learning framework.

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

A PyTorch implementation of DenseNet.

http://torch.ch