Info

この質問は閉じられています。 編集または回答するには再度開いてください。

Dependency of image size on detect with FasterRCNN

2 ビュー (過去 30 日間)
John Hipp
John Hipp 2018 年 2 月 5 日
閉鎖済み: MATLAB Answer Bot 2021 年 8 月 20 日
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?

この質問は閉じられています。

回答 (0 件)

この質問は閉じられています。

タグ

製品

Community Treasure Hunt

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

Start Hunting!

Translated by