Self-Tuning Incremental Model Compression Solution in Deep Neural Network with Guaranteed Accuracy Performance

摘要

A method of compressing a pre-trained deep neural network model includes inputting the pre-trained deep neural network model as a candidate model. The candidate model is compressed by increasing sparsity of the candidate, removing at least one batch normalization layer present in the candidate model, and quantizing all remaining weights into fixed-point representation to form a compressed model. Accuracy of the compressed model is then determined utilizing an end-user training and validation data set. Compression of the candidate model is repeated when the accuracy improves. Hyper parameters for compressing the candidate model are adjusted, then compression of the candidate model is repeated when the accuracy declines. The compressed model is output for inference utilization when the accuracy meets or exceeds the end-user performance metric and target.