https://github.com/fastmachinelearning/fastml-science

Implementations of the fastml-science bechmark models, including a standard Keras (float) and QKeras (quantized) implementations.
https://github.com/fastmachinelearning/fastml-science

edge machine-learning real-time science

Last synced: 10 months ago
JSON representation

Implementations of the fastml-science bechmark models, including a standard Keras (float) and QKeras (quantized) implementations.

• Host: GitHub
• URL: https://github.com/fastmachinelearning/fastml-science
• Owner: fastmachinelearning
• License: apache-2.0
• Created: 2022-01-06T14:58:46.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2023-01-16T03:20:51.000Z (about 3 years ago)
• Last Synced: 2025-03-27T15:52:13.923Z (10 months ago)
• Topics: edge, machine-learning, real-time, science
• Language: Python
• Homepage:
• Size: 11.9 MB
• Stars: 5
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Fast Machine Learning Science Benchmarks

[![DOI](https://zenodo.org/badge/445208377.svg)](https://zenodo.org/badge/latestdoi/445208377)

[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

Implementations of the `fastml-science` benchmark models, including a standard Keras (float) and QKeras (quantized) implementations.

# jet-classify

## Requirements:

Python 3.8

```

conda env create -f environment.yml

```

## Training:

```

python3 train.py -c 

```

Upon training completion, graphs for the ROC for each tagger, are saved to the output directory, along with a .h5 saved model file. 

The benchmark includes a float/unquantized 3 layer model as well as a uniformally quantized 6b model

## Sample Runs

### Training Float Baseline:

```

python3 train.py -c float_baseline.yml

```

![Alt text](jet-classify/model/float_baseline/keras_roc_curve.png?raw=true "Float Baseline ROC Curve")

`Model test accuracy = 0.766`

`Model test weighted average AUC = 0.943`

### Training Quantized Baseline:

```

python3 train.py -c quantized_baseline.yml

```

![Alt text](jet-classify/model/quantized_baseline/keras_roc_curve.png?raw=true "Quantized Baseline ROC Curve")

`Model test accuracy = 0.764`

`Model test weighted average AUC = 0.941`

# beam-control

WIP

# sensor-data-compression

WIP