Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

no code implementations • 30 Oct 2020 • Guangli Li, Xiu Ma, Xueying Wang, Lei Liu, Jingling Xue, Xiaobing Feng

The increasing computational cost of deep neural network models limits the applicability of intelligent applications on resource-constrained edge devices.

Network Pruning

LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units

no code implementations • 19 Mar 2020 • Guangli Li, Lei Liu, Xueying Wang, Xiu Ma, Xiaobing Feng

Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry.

Image Classification Quantization