The ONNX Model Zoo is a collection of pre-trained machine learning models in the ONNX format that have been contributed by community members. These models cover a range of tasks such as image classification, object detection, speech recognition, machine comprehension, and more. Each model in the zoo is accompanied by Jupyter notebooks for training and running inference, as well as links to the original papers describing the model architecture. The models can be downloaded from the GitHub repository and used with the ONNX backend. Some notable models in the zoo include MobileNet, ResNet, SqueezeNet, VGG, and AlexNet for image classification, as well as YOLOv2, SSD, and Mask-RCNN for object detection. Users are encouraged to contribute their own models to the zoo.
https://github.com/xetdata/onnx-models