Dr. Magic is a Senior Software Engineer living in Long Island, New York. He loves reading and writing. He is very interested in Computer Vision and Machine Learning. He has concentrated on image processing for more than five years.
This book used an RNN (Recurrent Neural Network) with a LSTM (Long-Short Term Memory) layer to recognize actions in videos coded with Python in Jupyter Notebook. The codes could be executed on both CPU and GPU. The highest prediction accuracy from the RNN was 86.97%, which was a little higher than that from an SVM (Support Vector Machines) classifier (86.09%).
This book implemented 6 algorithms to classify images with testing data prediction accuracy as primary criterion (30% ~ 90%) and time consumption as secondary one (seconds to 1 hour). Considering both of the criteria, the Pre-Trained AlexNet Features Representation plus a Classifier, such as the k-Nearest Neighbors (KNN) and the Support Vector Machines (SVM), was concluded as the best algorithm.