Imported Net from Caffe Missing Classification Labels

1 次查看（过去 30 天）
Miraç Gülgönül
Miraç Gülgönül 2019-9-12
回答： Shivam Sardana 2019-9-24
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?

请先登录，再回答此问题。

回答（1 个）

Shivam Sardana
Shivam Sardana 2019-9-24
There is a name-apir input 'Classes' argument which you can pass in importCaffeNetwork. You can refer to this documentation link for more detail:
https://www.mathworks.com/help/deeplearning/ref/importcaffenetwork.html#namevaluepairarguments
Hope this help.

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2019a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by