Tensorflow 2.0 is here, session is gone. This project uses tensorflow 2.0 to train a convolutional segmentation model, consisting of downsampling and upsampling layers.
Input imageSegmented image, animated over epochs.
YOLOv2 (You only look once) is one of the most popular algorithms for object detection. As the name implies, the predictions of objects, and their bounding boxes are calculated as a single forward pass through the convolutional neural network, making it suitable for real time object detection.
In this repository, I make custom preprocessing methods to be operated on the output of the YOLOv2, to detect common objects encountered while driving in an urban environment.
This program uses the COCO (Common Objects in Context) class list, which has 80 object categories. For reference, these classes are given in the file “coco_classes.txt”, …