The previous article introduces Object Detection. This article will introduce the concept of Image Segmentation, and explain how to train a custom image segmentation model using TensorFlow Object Detection API through cases, including data set collection and processing, TensorFlow Object Detection API installation, and model training. Mask R-CNN to be used in this article is an Instance Segmentation model. The installation of TensorFlow Object Detection API is consistent with the Object Detection, please refer to Previous, so I won't repeat it here. Note:!!! From here, please make sure to execute under the environment of conda od.