The TensorFlow Object Detection API is an open-source computer vision framework built on top of TensorFlow. It is used for building object detection and instance segmentation models that can localize multiple objects in the same image. This tutorial shows how to perform both task with OpenVINO Runtime.
This notebook consider how to convert the Faster R-CNN with Resnet-50 V1 Object Detection model and then detect objects in an image using OpenVINO Runtime.
This notebook also shows how to convert the Mask R-CNN with Inception ResNet V2 Instance Segmentation model and then segment instances in an image using OpenVINO Runtime.
This is a self-contained example that relies solely on its own code.
We recommend running the notebook in a virtual environment. You only need a Jupyter server to start. For details, please refer to Installation Guide.
