[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#818641: RFP: lasagne -- Lightweight library to build and train neural networks in Theano



Package: wnpp
Severity: wishlist
X-Debbugs-CC: debian@danielstender.com

* Package name    : lasagne
  Version         : git20160319
  Upstream Author : Lasagne contributors
* URL             : https://github.com/Lasagne/Lasagne
* License         : MIT
  Programming Lang: Python
  Description     : Lightweight library to build and train neural networks in Theano

Lasagne is a lightweight library to build and train neural networks in Theano. Its main features are:

- Supports feed-forward networks such as Convolutional Neural Networks (CNNs), recurrent networks including Long Short-Term Memory (LSTM), and any combination thereof
- Allows architectures of multiple inputs and multiple outputs, including auxiliary classifiers
- Many optimization methods including Nesterov momentum, RMSprop and ADAM
- Freely definable cost function and no need to derive gradients due to Theano's symbolic differentiation
- Transparent support of CPUs and GPUs due to Theano's expression compiler


Reply to: