Transfer Learning For Multi-Class Image Classification Using Deep Convolutional Neural Network

Image classification has become more interesting in the research field due to the development of new and high performing machine learning frameworks. With the advancement of artificial neural networks and the development of deep learning architectures such as the convolutional neural network, that is based on artificial neural networks has triggered the application of multiclass image classification and recognition of objects belonging to the multiple categories. Every latest machine learning framework has a comparative advantage over the older ones in terms of performance and complexity. In this article, we will implement the multiclass image classification using the VGG-19 Deep Convolutional Network used as a Transfer Learning framework where the VGGNet comes pre-trained on the ImageNet dataset. For the experiment, we will use the CIFAR-10 dataset and classify the image objects into 10 classes.