Theano Python Packages

aesara

Aesara is a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays.

returnn

The RWTH extensible training framework for universal recurrent neural networks

aesara-nightly

Aesara is a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays.

keras-resnet

Keras package for deep residual networks

aetros

AETROS CLI + SDK. Command line application to manage/monitor machine learning training in AETROS Trainer

dandelion

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

lasagne

Lightweight library to build and train neural networks in Theano

conx

The On-Ramp to Deep Learning

keras-rl

Deep Reinforcement Learning for Keras.

keras-vis

Neural network visualization toolkit for keras

symjax

Documentation:

theano-lstm

:microscope: Nano size Theano LSTM module

neuralnet

A high level framework for general purpose neural networks in Theano.

ucs

Implements the CAM02-UCS (Luo et al. (2006)) forward transform.

neuralnet-pytorch

A high level framework for general purpose neural networks in Pytorch.

pyfms

A Theano-based Python implementation of Factorization Machines (Rendle 2010).

keras-vis-temp

Neural network visualization toolkit for keras

sengbao-mle

翻新的最大似然估计框架 copied and renewed maximum likelihood estimation package

keras-rcnn

Keras package for region-based convolutional neural networks (RCNNs)

dipp

Library of custom Inverse-Problems-related add-ons for Deep Learning frameworks

conviz

Conviz is a convolutional neural network layer visualization library developed in Python and used with Keras.

keras-text

Text Classification Library in Keras

tnet

Torch and torchnet like library for building and training neural networks in Theano

yadll

Deep learning ultra light framework based on Theano