Info

이 질문은 마감되었습니다. 편집하거나 답변을 올리려면 질문을 다시 여십시오.

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

조회 수: 1 (최근 30일)
Joseph Stember
Joseph Stember 2017년 8월 10일
마감: MATLAB Answer Bot 2021년 8월 20일
For the Training Image Labeler, can you include images without the structure-of-interest to improve the RCNN training?

이 질문은 마감되었습니다.

답변 (1개)

Nick Choi
Nick Choi 2017년 8월 16일
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

이 질문은 마감되었습니다.

태그

Community Treasure Hunt

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

Start Hunting!

Translated by