Deep learning acceleration at the resource-constrained tactical edge.

Billy E. Geerhart,Venkat R. Dasari,Peng Wang, Brian Rapp

2023 IEEE International Conference on Big Data (BigData)（2023）

引用 0|浏览1

暂无评分

摘要

This paper outlines how we modified the torch2trt library which allowed us to build a recursive framework that can quantize previously unsupported PyTorch models. The framework partitions the PyTorch model into supported and unsupported modules, and then rebuilds the PyTorch model by replacing the supported PyTorch modules with faster TensorRT modules. The framework allows us to optimize and deploy more advanced Deep Neural Network algorithms that are not natively supported by torch2trt.

查看译文

关键词

quantization,PyTorch,inference acceleration,model reduction,deep neural networks,computer vision

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要