Assets

... optimizing your manufacturing processes with modular digital twins composed of expert assets...

icon

YOLOv5 OD Model in ONNX format

YOLOv5 Object Detector Model trained on 80 Common Object Classes

Model related to Artificial Intelligence Machine Learning in the context of Electronics Manufacturing & Equipment Food and Beverage Manufacturing Manufacturing Misc.

Provided by DFKI (German Research Center for Artificial Intelligence) 9 months, 3 weeks ago (last modified 4 months, 3 weeks ago); viewed 118 times and bound 3 times

Description:

The model yolov5s.zip file consists of

1. A yolov5s.onnx Object Detection Model, trained originally on COCO Dataset capable of detecting 80 different classes. The trained model is converted into ONNX format

2. A coco.names file which consisting of the class names, that the model has been trained on. It also gives all the list of classes the model can able to predict.

The Model can detect the following 80 classes on the images:

person, bicycle, car, motorbike, aeroplane, bus, train, truck, boat, traffic light, fire hydrant, stop sign, parking meter, bench, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, suitcase, frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket, bottle, wine glass, cup, fork, knife, spoon, bowl, banana, apple, sandwich, orange, broccoli, carrot, hot dog, pizza, donut, cake, chair, sofa, potted plant, bed, dining table, toilet, tv monitor, laptop, mouse, remote, keyboard, cell phone, microwave, oven, toaster, sink, refrigerator, book, clock, vase, scissors, teddy bear, hair drier, toothbrush


For a custom usage, the yolov5s.onnx Model and the coco.names files have to be updated with the custom files (keeping the same names) and shall be zipped as a single yolov5s.zip file. The custom class names shall follow the standard structure as given in coco.names file.

Use the Microservice OD & Counter Inference Service: COCO format with Metrics for easy inferences. The unzipped model files shall be available on /odapi/od_app/model folder for this Microservice to work.