Mastering Computer Vision with TensorFlow 2.x

Summary

In this chapter, we learned about the architectures of different convolution networks (ConvNet) and how different layers of a ConvNet are stacked together to classify various inputs into predefined classes. We learned different image classification models, such as AlexNet, VGGNet, Inception, and ResNet, why they are different, what problems they solve, and their overall similarities.

We learned about object detection methods, such as R-CNN, and how it got transformed over time into fast and faster R-CNN for bounding-box detection. The chapter introduced two new models, GAN and GNN, as two new sets of neural networks. The chapter ended with an introduction to reinforcement learning and transfer learning. We learned that in reinforcement ...