Convolutional Neural Networks in Tensorflow
Niha Kamal Basha, Surbhi Bhatia Khan, Abhishek Kaushal Kumar, Arwa Mashat · 2023
Among deep learning models, convolutional neural network (CNN) is an algorithm, which acts as an artificial neuron (neural network). This neural network has been widely used to deal with image input for image processing/recognition/classification. This chapter discusses the working of CNN with its architecture and applicability of CNN using python programing. CNN consist of important three layers for processing an input. They are convolution layer, fully-connected layer, and pooling layer. To implement the working of CNN using TensorFlow will be discussed in the chapter. The TensorFlow is capable of implementing 3D array, flexibility to iterate, faster model training and run more experiments. When these implementations are extended for production they have been run on large scale GPUs. The Kera is capable of implementing 3D array, flexibility to iterate, faster model training and run more experiments, also capable of building CNN model.