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 This package allows for use of python-lasagne with Python 3.
Release | Stable | Testing |
---|---|---|
Fedora Rawhide | 0.1-21.fc35 | - |
Fedora 35 | 0.1-21.fc35 | - |
Fedora 34 | 0.1-19.fc34 | - |
You can contact the maintainers of this package via email at
python-lasagne dash maintainers at fedoraproject dot org
.