Imported Net from Caffe Missing Classification Labels
显示 更早的评论
When I import a pre-trained Caffee net with importCaffeNetwork including the .prototxt and .caffemodel files and look at the last layer to see the classification labels it outputs:
ClassificationOutputLayer with properties:
Name: 'ClassificationOutput'
Classes: [class1 class2 class3 class4 class5 class6 class7]
OutputSize: 7
Hyperparameters
LossFunction: 'crossentropyex'
I would assume that these labels are included in the files, so why are they missing here?
回答（1 个）
Shivam Sardana
2019-9-24
0 个投票
There is a name-apir input 'Classes' argument which you can pass in importCaffeNetwork. You can refer to this documentation link for more detail:
Hope this help.
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
2019-9-12
2019-9-24
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
