Counting 3,834 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Author
Last Commit
Apr. 22, 2019
Created
Apr. 12, 2019

ONNXCV

Alpha release

Welcome to ONNXCV

Welcome to OnnxCV! OnnxCV (Open Neural Network EXchange Runtime for Computer Vision) is an inference engine for realtime computer vision, built upon ONNX Runtime and OpenCV.

To learn more about ONNX, go to their Github repo here or their website here. To learn more about OpenCV, go to their repo here or their website here.

Quickstart

Install ONNXCV by invoking the following command in a terminal or command prompt: pip install onnxcv

Create a new directory and download the ResNet model. Copy and paste the following script in your code:

from  onnxcv import ImageClassifier
clf = ImageClassifier('resnet18v1.onnx')
clf.run()

clf.run() initiates the device camera to show a visual output. The camera data will then be converted into the model compatible array to allow the model to make predictions. The predictions are arrays that are shown in the terminal.

To Do:

  • Finish documentation (ETA: 1 day)