Info

Cette question est clôturée. Rouvrir pour modifier ou répondre.

Dependency of image size on detect with FasterRCNN

2 vues (au cours des 30 derniers jours)
John Hipp
John Hipp le 5 Fév 2018
Clôturé : MATLAB Answer Bot le 20 Août 2021
I trained a fasterRCNN to detect left and right knees in bilateral knee x-rays using VGG-16. The accuracy reported in step 4 was near 100% at the end of training. The trained network works great - if I resize the input x-ray to just the right size - by trial&error. Is anyone aware of any documentation regarding this dependency and what was done with the image size during training such that it could achieve such high accuracy on the minibatches?

Cette question est clôturée.

Réponses (0)

Cette question est clôturée.

Tags

Produits

Community Treasure Hunt

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

Start Hunting!

Translated by