Skip to main content

Inference eNgine uSing aPproximate arithmEtic ComponenTs for Neural Networks

Project description

# inspect-nn : simPle sImulator for Neural nEtworks using APProximate muLtipliErs (written in python)

inspect-nn is a simulation tool for measuring the classification accuracy loss due to the use of approximate multipliers (i.e., multipliers designed by exploiting the [approximate computing design paradigm](https://link.springer.com/book/10.1007/978-3-030-94705-7)) in neural networks.

It has been developed to easily do porting of keras/tensorflow models, and to use the GPU to simulate a neural network while using approximate arithmetic units quickly and almost effortlessly.

Anyway, it is still under development!

## Installing the module You can install this module using `pip` `bash $ pip install inspect-nn `

## Using inspect-nn

Project details


Download files

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

Source Distribution

inspectnn-0.0.1.tar.gz (8.6 kB view hashes)

Uploaded Source

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