简体   繁体   English

在完全连接计算之前,Caffe如何在Blob上隐式重塑?

[英]How Caffe implicitly do reshape on a blob before doing fully connecting calculation?

在进行完全连接计算之前,Caffe如何隐式地对Blob进行整形?

"InnerProduct" layer (aka "fully connected") has a axis: parameter that defines how caffe "flattens" the blob for the inner product. "InnerProduct"层(也称为“完全连接”)具有axis:参数,用于定义caffe如何“展平”内部产品的斑点。
You can see in inner_product_layer.cpp : 您可以在inner_product_layer.cpp看到:

 // Dimensions starting from "axis" are "flattened" into a single // length K_ vector. For example, if bottom[0]'s shape is (N, C, H, W), // and axis == 1, N inner products with dimension CHW are performed. 

Since caffe stores Blobs contiguously in memory, no explicit reshape is needed for "flattening" the trailing dimensions of a blob. 由于caffe将Blob连续存储在内存中,因此无需显式重塑即可“展平” Blob的尾随尺寸。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM