Semantic Segmentation is an image analysis task in which we classify each pixel in the image into a class. It is runnning with the backbone of Fully-connected layer of Resnet 101 architecture.It is pre-trained in PASCAL VOC dataset which is used t classify 20 different classes. The segmentation code is built on top of the Resnet layer to segment various images Download the jupyter file and place the image needs to be segmented and run the file.