Info

Cette question est clôturée. Rouvrir pour modifier ou répondre.

For the Training Image Labeler, can you include images without the structure-of-interest to improve the RCNN training?

1 vue (au cours des 30 derniers jours)
Joseph Stember
Joseph Stember le 10 Août 2017
Clôturé : MATLAB Answer Bot le 20 Août 2021
For the Training Image Labeler, can you include images without the structure-of-interest to improve the RCNN training?

Cette question est clôturée.

Réponses (1)

Nick Choi
Nick Choi le 16 Août 2017
You could provide more images without the structure of interest to the Training Image Labeler but there is no guarantee that it would improve the performance of the RCNN. It depends on the data set but including more images without the structure of interest can have trade offs as mentioned in this doc link: https://www.mathworks.com/help/vision/ug/train-a-cascade-object-detector.html#btu4ez9-1

Cette question est clôturée.

Tags

Community Treasure Hunt

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

Start Hunting!

Translated by