Skip to main content

Keras-based framework for AI on the Edge

Project description


Keras-based framework for AI on the Edge

aXeleRate streamlines training and converting computer vision models to be run on various platforms with hardware acceleration. It is optimized for both the workflow on local machine and on Google Colab. Currently supports trained model conversion to: .kmodel(K210), .tflite formats. Support planned for: .tflite(Edge TPU), .pb(TF-TRT optimized).

Standford Dog Breed Classification Dataset VGG16 backend + Classifier Open In Colab PASCAL-VOC 2012 Object Detection Dataset MobileNet7_5 backend + YOLOv2 Open In Colab PASCAL-VOC 2012 Semantic Segmentation MobileNet7_5 backend + Segnet-Basic Open In Colab



aXeleRate is meant for people who need to run computer vision applications(image classification, object detection, semantic segmentation) on the edge devices with hardware acceleration. It has easy configuration process through config file or config dictionary(for Google Colab) and automatic conversion of the best model for training session into the required file format. You put the properly formatted data in, start the training script and (hopefully) come back to see a converted model that is ready for deployment on your device!

:wrench: Key Features

  • Supports multiple computer vision models: object detection(YOLOv2), image classification, semantic segmentation(SegNet-basic)
  • Different feature extractors to be used with the above network types: Full Yolo, Tiny Yolo, MobileNet, SqueezeNet, VGG16, ResNet50, and Inception3.
  • Automatic conversion of the best model for the training session. aXeleRate will download the suitable converter automatically.
  • Currently supports trained model conversion to: .kmodel(K210), .tflite formats. Support planned for: .tflite(Edge TPU), .pb(TF-TRT optimized).
  • Model version control made easier. Keras model files and converted models are saved in the project folder, grouped by the training date. Training history is saved as .png graph in the model folder.
  • Two modes of operation: locally, with script and .json config file and remote, tailored for Google Colab, with module import and dictionary config.

💾 Install

Stable version:

pip install axelerate

Daily development version:

pip install git+

:computer: Project Story

aXeleRate started as a personal project of mine for training YOLOv2 based object detection networks and exporting them to .kmodel format to be run on K210 chip. I also needed to train image classification networks. And sometimes I needed to run inference with Tensorflow Lite on Raspberry Pi. As a result I had a whole bunch of disconnected scripts each had somewhat overlapping functionality. So, I decided to fix that and share the results with other people who might have similiar workflows.

aXeleRate is still work in progress project. I will be making some changes from time to time and if you find it useful and can contribute, PRs are very much welcome!

:ballot_box_with_check: TODO list:

  • [ ] Porting to tf.keras and Tensorflow 2
  • [ ] Adding support for multi-GPU and Cloud TPU training
  • [ ] Unifiying image augumentation pipeline
  • [ ] SegNet to use common encoders(currently SegNet uses it's own feature extractors as encoder part)


Project details

Release history Release notifications

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for axelerate, version 0.5.2
Filename, size File type Python version Upload date Hashes
Filename, size axelerate-0.5.2-py3-none-any.whl (72.6 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size axelerate-0.5.2.tar.gz (55.3 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page