我怎么知道“偏见"是否存在?存在于一层中? [英] How can i know whether "bias" exists in a layer?

问题描述

我正在尝试通过pycaffe读取caffe网络中的体重和偏见. 这是我的代码

I'm trying to read weight and bias in a caffe network with pycaffe. Here is my code

weight = net.params[layer_name][0].data
bias = net.params[layer_name][1].data

但是，我的网络中的某些层没有偏差，因此会出现错误Index out of range.

But, some layers in my network has no bias, so that there will be an error which is Index out of range.

所以我的问题是我可以使用

So my question is can I use

if(net.params[layer_name][1] exists):
    bias = net.params[layer_name][1].data

控制对bias的分配? 以及如何编写代码?

to control the assignments to bias? And how to write the code?

推荐答案

您可以简单地遍历net.params[layer_name]:

layer_params = [blob.data for blob in net.params[layer_name]]

这样，您将获得全部layer_params(对于某些图层，它可能大于2，例如， )

This way, you get all layer_params (which might be more than 2 for some layers, e.g., "BatchNorm")

如果只想检查第二个参数blob，则可以使用len:

If you only want to check for the second parameters blob, you can use len:

if len(net.params[layer_name]) >= 2:
    bias = net.params[layer_name][1].data

---

PS，
可能net.params[layer_name]并非完全是python list，而是某些python boost wrapper对象，因此您可能需要在我在此建议的某些方法中将其显式转换为列表(list(net.params[layer_name])).答案.

---

PS,
It might be the case that net.params[layer_name] is not exactly a python list, but rather some python boost wrapper object, thus you might need to explicitly cast it to list (list(net.params[layer_name])) in some of the methods I suggested in this answer.

这篇关于我怎么知道“偏见"是否存在?存在于一层中?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！