Keras model and weights for GarNet-on-FPGA

Source code and input weights data for GarNet-on-FPGA This repository contains the Keras layer and model files for the simultaneous regression and classification task described in arXiv:2008.03601. Dataset in 10.5281/zenodo.3888910 can be fed into the training script (train.py) to reproduce the results in the paper. The GarNet layer file (garnet.py) is a partial copy from the original at commit 6d1127d. The hls4ml configuration and weights files for the "continuous" and "quantized" models in the paper (Vmax = 128) are also packaged together in the tarball hls4ml_inputs.tar.gz. HLS workspaces can be created from the input files with hls4ml version > v0.3.0 (commit e86c103 and later)

Related Organizations

European Organization for Nuclear Research
Switzerland

Keywords

Particle reconstruction, Fast inference, hls4ml, Graph neural network, Particle identification, Keras

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average