Skip to content

Latest commit

 

History

History
36 lines (26 loc) · 928 Bytes

README.md

File metadata and controls

36 lines (26 loc) · 928 Bytes

keras-conv1d

Description

Code for training and evaluating 1D convolutional neural network with Keras. Use multiple channels and filters to explore conv1d options for HLS4ML project.

The example is for the raw, inertial signals of this dataset.

Setup

Install all dependencies using miniconda (from HLS4ML project)):

Install miniconda2 by sourcing install_miniconda.sh in your home directory. Log out and log back in after this.

cp install_miniconda.sh ~/
cd ~
source install_miniconda.sh

Install the rest of the dependencies:

cd ~/keras-conv1d
source install.sh

Each time you log in set things up:

source setup.sh

Run

cd train
python keras_conv1d.py