Skip to main content

NNKit: A Python framework for creating dynamic neural networks.

Project description

NNKit: A Python framework for creating dynamic neural networks

NNKit is a framework for creating and training neural network models, based on dynamic computation graphs. See this post for more info on how the framework works.

Dependencies:

Installation:

You can pip install nnkit, in which case Numpy will also be installed. Otherwise you can download the source and manually install numpy if necessary.

Modules:

The following is a list of modules, nodes and optimizers, along with the framework version in which they were added.

activation:

  • ReLU (1.0)
  • LReLU (1.0)
  • Sigmoid (1.0)
  • Tanh (1.0)
  • Softmax (1.0)

arithmetic:

  • Multiply (1.0)
  • Add (1.0)

loss:

  • L1 (1.0)
  • L2 (1.0)
  • Cross Entropy (1.0)
  • Huber (1.4.0)

normalization:

  • Batch Normalization (1.0)

regularization:

  • L2 (1.0)
  • Dropout (1.0)

optimization:

  • Gradient descent / momentum (1.0)
  • Adam / RMSProp (1.0)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
nnkit-1.4.2.tar.gz (9.3 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page