The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

Lightweight library to build and train neural networks in Theano

CUDA Templates for Linear Algebra Subroutines

Keras.NET is a high-level neural networks API, written in C# with Python Binding and capable of running on top of TensorFlow, CNTK, or Theano.

Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

The Cutest Deep Learning Framework which is also a wonderful Declarative Language

Tiny and elegant deep learning library

A lightweight deep learning library

A collection of all projects pertaining to different layers in the SDC software stack

N2D2 is a open source CAD framework for Deep Neural Network simulation and full DNN-based applications building.

Flow-based data pre-processing for deep learning

Demitasse is a fast Deep Neural Network Library for mobile devices(non GPGPU).

A keras-like API deep learning framework,realized by Numpy only.Support CNN, RNN, LSTM, Dense, etc.

Library for learning and inference with Sum-product Networks

A tensorflow batteries included kit to write tensorflow networks from scratch or use existing ones.

A light weight deep learning framework, on top of Theano, offering better balance between flexibility and abstraction

VQA - Visual Question Answering

YOLOv2 of Windows (VS2013update5, 64) version for object detection.

Breast Cancer Detection classifier built from the The Breast Cancer Histopathological Image Classification (BreakHis) dataset composed of 7,909 microscopic images of breast tumor tissue collected from 82 patients using different magnifying factors (40X, 100X, 200X, and 400X). To date, it contains 2,480 benign and 5,429 malignant samples (700X460 pixels, 3-channel RGB, 8-bit depth in each channel, PNG format). This database has been built in collaboration with the P&D Laboratory - Pathological Anatomy and Cytopathology, Parana, Brazil.

C# library for easy Deep Learning and Deep Reinforcement Learning. It is wrapper over C# CNTK API. Has implementation of layers (LSTM, Convolution etc.), optimizers, losses, shortcut-connections, sequential model, sequential multi-output model, agent teachers, policy gradients, actor-critic etc. Contains helpers for work with dataset (split, statistics, SMOTE etc). Allows train, evaluate and inference deep neural networks in style similar to Keras.

Neural network from scratch in Python using Numpy

ToeffiPy is a PyTorch like autograd/deep learning library based only on numpy.

An Infant Library of Artificial Neural Network (multilayer-deep-convolutional-machine-learning)

轻量、易于修改、可组层训练的神经网络 / Lightweight Greedy Layer-Wise Training Neural Network

A minimalist neural networks library built on a tiny autograd engine

Python libraries for the Voice Conversion TFG

Vortex (Virtual Cortex) Neural Network / Deep learning library

Deep learning library, new to everything!

Artificial Neural Network Interface Engine