我在哪里可以找到经过训练的模型(如 googleNet 的输出)与真实类别标签之间的标签映射? [英] Where can I find the label map between trained model like googleNet's output to there real class label?
问题描述
大家,我是咖啡新手.目前,我尝试使用从模型动物园下载的经过训练的 GoogleNet 对一些图像进行分类.然而,网络的输出似乎是一个向量而不是真正的标签(如狗、猫).我在哪里可以找到经过训练的模型(如 googleNet 的输出)与其真实类别标签之间的标签映射?谢谢.
everyone, I am new to caffe. Currently, I try to use the trained GoogleNet which was downloaded from model zoo to classify some images. However, the network's output seem to be a vector rather than real label(like dog, cat). Where can I find the label-map between trained model like googleNet's output to their real class label? Thanks.
推荐答案
如果你从 git 得到 caffe
你应该在 data/ilsvrc12
文件夹中找到一个 shell 脚本 get_ilsvrc_aux.sh
.
此脚本应下载用于 ilsvrc(用于大规模图像识别挑战的 imagenet 子集)训练的几个文件.
If you got caffe
from git you should find in data/ilsvrc12
folder a shell script get_ilsvrc_aux.sh
.
This script should download several files used for ilsvrc (sub set of imagenet used for the large scale image recognition challenge) training.
将要下载的最有趣的文件(对你来说)是 synset_words.txt
,这个文件有 1000 行,网络识别的每个类一行.
行的格式为
The most interesting file (for you) that will be downloaded is synset_words.txt
, this file has 1000 lines, one line per class identified by the net.
The format of the line is
nXXXXXXXX 类描述
nXXXXXXXX description of class
这篇关于我在哪里可以找到经过训练的模型(如 googleNet 的输出)与真实类别标签之间的标签映射?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!