Skip to main content

Infrastructure for support neural networks compression

Project description

Model Compression Toolkit (MCT) Quantizers

The MCT Quantizers library is an open-source library developed by researchers and engineers working at Sony Semiconductor Israel.

It provides tools for easily representing a quantized neural network in both Keras and PyTorch. The library offers researchers, developers, and engineers a set of useful quantizers, along with a simple interface for implementing new custom quantizers.

High level description:

The library's quantizers interface consists of two main components:

  1. QuantizationWrapper: This object takes a layer with weights and a set of weight quantizers to infer a quantized layer.
  2. ActivationQuantizationHolder: An object that holds an activation quantizer to be used during inference.

Users can set the quantizers and all the quantization information for each layer by initializing the weights_quantizer and activation_quantizer API.

Please note that the quantization wrapper and the quantizers are framework-specific.

Quantizers:

The library provides the "Inferable Quantizer" interface for implementing new quantizers. This interface is based on the BaseInferableQuantizer class, which allows the definition of quantizers used for emulating inference-time quantization.

On top of BaseInferableQuantizer the library defines a set of framework-specific quantizers for both weights and activations:

  1. Keras Quantizers
  2. Pytorch Quantizers

The mark_quantizer Decorator

The @mark_quantizer decorator is used to assign each quantizer with static properties that define its task compatibility. Each quantizer class should be decorated with this decorator, which defines the following properties:

  • QuantizationTarget: An Enum that indicates whether the quantizer is intended for weights or activations quantization.
  • QuantizationMethod: A list of quantization methods (Uniform, Symmetric, etc.).
  • identifier: A unique identifier for the quantizer class. This is a helper property that allows the creation of advanced quantizers for specific tasks.

Getting Started

This section provides a quick guide to getting started. We begin with the installation process, either via source code or the pip server. Then, we provide a short example of usage.

Installation

From PyPi - mct-quantizers package

To install the latest stable release of MCT Quantizer from PyPi, run the following command:

pip install mct-quantizers

If you prefer to use the nightly package (unstable version), you can install it with the following command:

pip install mct-quantizers-nightly

From Source

To work with the MCT Quantizers source code, follow these steps:

git clone https://github.com/sony/mct_quantizers.git
cd mct_quantizers
python setup.py install

Requirements

To use MCT Quantizers, you need to have one of the supported frameworks, Tensorflow or PyTorch, installed.

For use with Tensorflow, please install the following package: tensorflow,

For use with PyTorch, please install the following package: torch

You can also use the requirements file to set up your environment.

License

Apache License 2.0.

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

Built Distribution

File details

Details for the file mct-quantizers-nightly-1.4.0.20240113.post1054.tar.gz.

File metadata

File hashes

Hashes for mct-quantizers-nightly-1.4.0.20240113.post1054.tar.gz
Algorithm Hash digest
SHA256 928f78e900a5293d256916b86b563ec4453e181c65e3a096f3db61194708a1c2
MD5 3b88c4276e87d7f9017d3ad9175a7057
BLAKE2b-256 245ceec2104bc69126bd2fe11be7c83d39b61ccb8593e6c9ef2c3c537505659b

See more details on using hashes here.

File details

Details for the file mct_quantizers_nightly-1.4.0.20240113.post1054-py3-none-any.whl.

File metadata

File hashes

Hashes for mct_quantizers_nightly-1.4.0.20240113.post1054-py3-none-any.whl
Algorithm Hash digest
SHA256 1770383611f5a18aa6971582606122c61b20060660ab01e2b7ca2b947e378c03
MD5 fdcccaca79c0bc939bcd6fe6bd86918a
BLAKE2b-256 ef03c2f7a2a87daf9695658fc9bec5924da1e77743d382b3a5adc01a0c3d92a9

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page