Imported Net from Caffe Missing Classification Labels
2 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
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?
0 Commenti
Risposte (1)
Shivam Sardana
il 24 Set 2019
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.
0 Commenti
Vedere anche
Categorie
Scopri di più su Image Data Workflows in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!