DeepShift: Towards Multiplication-Less Neural Networks

View Researcher's Other Codes

Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).

Please contact us in case of a broken link from here

Authors Joey Yiwei Li, Zihao Chen, Ye Henry Tian, Farhan Shafiq, Mostafa Elhoushi
Journal/Conference Name arXiv preprint
Paper Category
Paper Abstract Deployment of convolutional neural networks (CNNs) in mobile environments, their high computation and power budgets proves to be a major bottleneck. Convolution layers and fully connected layers, because of their intense use of multiplications, are the dominant contributer to this computation budget. This paper proposes to tackle this problem by introducing two new operations convolutional shifts and fully-connected shifts, that replace multiplications all together with bitwise shift and sign flipping instead. For inference, both approaches may require only 6 bits to represent the weights. This family of neural network architectures (that use convolutional shifts and fully-connected shifts) are referred to as DeepShift models. We propose two methods to train DeepShift models DeepShift-Q that trains regular weights constrained to powers of 2, and DeepShift-PS that trains the values of the shifts and sign flips directly. Training the DeepShift versions of ResNet18 architecture from scratch, we obtained accuracies of 92.33% on CIFAR10 dataset, and Top-1/Top-5 accuracies of 65.63%/86.33% on Imagenet dataset. Training the DeepShift version of VGG16 on ImageNet from scratch, resulted in a drop of less than 0.3% in Top-5 accuracy. Converting the pre-trained 32-bit floating point baseline model of GoogleNet to DeepShift and training it for 3 epochs, resulted in a Top-1/Top-5 accuracies of 69.87%/89.62% that are actually higher than that of the original model. Further testing is made on various well-known CNN architectures. Last but not least, we implemented the convolutional shifts and fully-connected shift GPU kernels and showed a reduction in latency time of 25\% when inferring ResNet18 compared to an unoptimized multiplication-based GPU kernels. The code is available online at https//
Date of publication 2019
Code Programming Language Python

Copyright Researcher 2022