首页>
外国专利>
EFFICIENT INFERENCING WITH FAST POINTWISE CONVOLUTION
EFFICIENT INFERENCING WITH FAST POINTWISE CONVOLUTION
展开▼
机译:快速推断快速卷积
展开▼
页面导航
摘要
著录项
相似文献
摘要
Embodiments described herein relate to a method, comprising: receiving input data at a convolutional neural network (CNN) model; generating a factorized computation network comprising a plurality of connections between a first layer of the CNN model and a second layer of the CNN model, wherein: the factorized computation network comprises N inputs, the factorized computation network comprises M outputs, and the factorized computation network comprises at least one path from every input of the N inputs to every output of the M outputs; setting a connection weight for a plurality of connections in the factorized computation network to 1 so that a weight density for the factorized computation network is < 100%; performing fast pointwise convolution using the factorized computation network to generate fast pointwise convolution output; and providing the fast pointwise convolution output to the second layer of the CNN model.
展开▼
机译:本文描述的实施例涉及一种方法,包括:在卷积神经网络(CNN)模型处接收输入数据;生成包括多个连接的分解计算网络,包括多个连接的CNN模型和第二层模型的第二层之间的连接,其中:分解计算网络包括 n 输入,分子计算网络包括 M 输出,并且分解计算网络包括从 n 输入的每个输入到每个输出输出的至少一个路径;在将区分计算网络中设置多个连接的连接权重为1,使得分解计算网络的权重密度<100%;使用分解计算网络执行快速点卷积以产生快速卷积输出;并为CNN模型的第二层提供快速卷积输出。
展开▼