There is a newer version of the record available.

Published March 31, 2020 | Version v0.2.0
Software Open

hls-fpga-machine-learning/hls4ml: v0.2.0

Creators

  • 1. CERN
  • 2. Fermi National Accelerator Laboratory
  • 3. UC San Diego
  • 4. HawkEye 360
  • 5. University of Illinois at Chicago
  • 6. University of Tokyo
  • 7. Rhodes College
  • 8. Massachusetts Institute of Technology

Description

What's new:

  • tf_to_hls: convert tensorflow protobuf (.pb) models to HLS projects
  • Support for Keras model .h5 files (extending existing support for .json architecture + .h5 weights format)
  • Support larger Conv1D / 2D layers
  • Support for binary and ternary layers from QKeras
  • API enhancements for addition of custom layer and new backends
  • Keras and HLS model profiling tool
  • hls4ml report command to gather HLS build reports
  • hls4ml build -l command to run logic synthesis
  • Fused Batch Normalization and Dense layer optimization pass

Files

hls-fpga-machine-learning/hls4ml-v0.2.0.zip

Files (5.5 MB)

Name Size Download all
md5:3186497acf355acee44aa7acf6dee9da
5.5 MB Preview Download

Additional details

Related works

Is supplement to
https://github.com/hls-fpga-machine-learning/hls4ml/tree/v0.2.0 (URL)