commit | 3aa5f7407fe11bc366a02945153865559c2f1a4d | [log] [tgz] |
---|---|---|
author | mxiangyue <mxiangyue@gmail.com> | Fri Nov 12 10:06:02 2021 +1100 |
committer | mxiangyue <mxiangyue@gmail.com> | Fri Nov 12 10:06:02 2021 +1100 |
tree | aafa7a648dbb3676938763112efdb0e2d761dc4d | |
parent | 0414272e301a41a9996988e1f6e748dfdd7891a2 [diff] |
add README
This project implements a pre-trained fully connected neural network (FCNN) for hand-written digits from MNIST dataset. It takes images from MNIST dataset (28x28) and output single digit prediction. All parameters (weights and bias) are pre-trained and hard-coded. User can use wishbone bus to pass in inputs and obtain outputs.
This repository contains a Verilog implementation of the FCNN, targeting the OpenLane flow for the Skywater 130nm process and is an entry for the Google/Efabless MPW-3 shuttle.