Skip to main content

Meta-framework for faster prototyping in Deep Learning

Project description

Braid is a flexible and modular neural network library. It is written in python and uses Tensorflow backend. It was designed for fast development and at the same time to be able to support arbitrary network designs.

The main ideas guiding the design of braid were:

Flexibility: There should be multiple ways to interact with the library. Design the network in Tensorflow, braid or simply provide it in a protobuf file.

Openness: Keep the Tensorflow backend open rather than behind layers of abstraction. It helps in modifying existing structures instead of building from ground up for unavailable network attributes and nodes.

Modularity: The structure of the library should not be rigid. User should be able to modify parts of library according to preference.

Braid has enough functionality built-in to support most complex network and support for building completely custom nodes and layers.

It is compatible with: Python 2.7-3.5

Braid is useful when:

  • You require fast experimentation and don’t want to bother with boilerplate parts of the code.
  • You want to customize parts of network and still want to retain the simplicity of code.
  • You need to customize/streamline the entire existing library according to given specification or personal preferences.

Installation

pip install braid

If the above does not work then(requires git):

pip install git+git://github.com/Arya-ai/braid

Project details


Release history Release notifications | RSS feed

This version

0.1

Download files

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

Files for Braid, version 0.1
Filename, size File type Python version Upload date Hashes
Filename, size braid-0.1-py2-none-any.whl (49.9 kB) File type Wheel Python version 2.7 Upload date Hashes View
Filename, size braid-0.1.tar.gz (32.9 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page