Is it possible to use Alexnet to classify multiple objects in a single image?
조회 수: 7 (최근 30일)
I'm trying to identify thousands of objects in a mosaic image. I have split this mosaic into several 227x227 images, but I would like alexnet to be able to classify several objects in each 227x227 image (think a star map in 227x227, where alexnet will be classifying 5 different types of stars. The problem isn't as complex as this, but the scale is similar).
Is there a way to get alexnet to do this?
Delprat Sebastien 2020년 1월 6일
편집: Delprat Sebastien 님. 2020년 1월 6일
You need to use another kind of network. Basically a so called Fast-R network will reuse an existing network (Alexnet for instance) to detect multiple objects into an image. You will also need another dataset with many images and their associated objects to be detected:ROI (bounding boxes for all the detected objects) and object classe. The doc has an example about that.
Actually, you may use a pretrained YOLO network that works well for many applications (and it is already trained, so no long and difficult training).