From b4130deac145f8b5ee64e7307ab07ff096a3cd27 Mon Sep 17 00:00:00 2001 From: AIWintermuteAI Date: Tue, 14 Dec 2021 14:27:03 +0100 Subject: [PATCH] version bump to 0.7.5 --- README.md | 10 +++++----- setup.py | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index dd6b16a..5dabafc 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@

-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(Ubuntu 18.04 - other Linux distros might work, but not tested. Mac/Win OS are not supported) and on Google Colab. Currently supports trained model conversion to: .kmodel(K210), .tflite format(full integer and dymaic range quantization support available), OpenVINO IR model format. Experimental support: Google Edge TPU. +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(Ubuntu 18.04/20.04 - other Linux distributions might work, but not tested. Mac OS/Windows are not supported) and on Google Colab. Currently supports trained model conversion to: .kmodel(K210), .tflite format(full integer and dynamic range quantization support available), .onnx formats. Experimental support: Google Edge TPU.

@@ -14,7 +14,7 @@ aXeleRate streamlines training and converting computer vision models to be run o -
Standford Dog Breed Classification Dataset NASNetMobile backend + Classifier Open In Colab PASCAL-VOC 2012 Object Detection Dataset MobileNet1_0 backend + YOLOv2 + PASCAL-VOC 2012 Object Detection Dataset MobileNet1_0 backend + YOLOv3 Open In Colab Human parsing Semantic Segmentation MobileNet5_0 backend + Segnet-Basic @@ -35,10 +35,10 @@ TL;DR 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) + - Supports multiple computer vision models: object detection(YOLOv3), image classification, semantic segmentation(SegNet-basic) - Different feature extractors to be used with the above network types: Full Yolo, Tiny Yolo, MobileNet, SqueezeNet, NASNetMobile, ResNet50, and DenseNet121. - 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 format(full integer and dymaic range quantization support available), .tflite(Edge TPU), .onnx(for later on-device optimization with TensorRT), OpenVINO IR model and .blob (for inference with Movidius chipes, such as OpenCV AI Kit). + - Currently supports trained model conversion to: .kmodel(K210), .tflite format(full integer and dynamic range quantization support available), .tflite(Edge TPU), .onnx(for later on-device optimization with TensorRT). - 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 train.py script and .json config file and remote, tailored for Google Colab, with module import and dictionary config. @@ -56,7 +56,7 @@ If installing in Anaconda environment, make sure you have necessary CUDA/CUDNN v ### :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 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 similar 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! diff --git a/setup.py b/setup.py index c58ee2e..9d07336 100644 --- a/setup.py +++ b/setup.py @@ -9,7 +9,7 @@ requirements = f.read().splitlines() setup(name='axelerate', - version="0.7.0", + version="0.7.5", description='Keras-based framework for AI on the Edge', install_requires=requirements, long_description=long_description,