Hummingbird logo


Compile trained ML models into tensor computation (By Microsoft)
+ 1

What is Hummingbird?

It is a library for compiling trained traditional ML models into tensor computations. It allows users to seamlessly leverage neural network frameworks (such as PyTorch) to accelerate traditional ML models.
Hummingbird is a tool in the Machine Learning Tools category of a tech stack.
Hummingbird is an open source tool with 3K GitHub stars and 247 GitHub forks. Here’s a link to Hummingbird's open source repository on GitHub

Who uses Hummingbird?

4 developers on StackShare have stated that they use Hummingbird.

Hummingbird Integrations

Linux, PyTorch, scikit-learn, Windows, and macOS are some of the popular tools that integrate with Hummingbird. Here's a list of all 6 tools that integrate with Hummingbird.

Hummingbird's Features

  • Current and future optimizations implemented in neural network frameworks
  • Native hardware acceleration
  • Convert your trained traditional ML models into PyTorch

Hummingbird Alternatives & Comparisons

What are some alternatives to Hummingbird?
It is a document automation platform and suite that empowers users to cut document prep time in half by automatically converting existing documents to standardized smart-templates.
It is a free web-based bug tracking system. It provides a delicate balance between simplicity and power. Users are able to get started in minutes and start managing their projects while collaborating with their teammates and clients effectively.
TensorFlow is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.
PyTorch is not a Python binding into a monolothic C++ framework. It is built to be deeply integrated into Python. You can use it naturally like you would use numpy / scipy / scikit-learn etc.
scikit-learn is a Python module for machine learning built on top of SciPy and distributed under the 3-Clause BSD license.
See all alternatives

Hummingbird's Followers
9 developers follow Hummingbird to keep up with related blogs and decisions.