I am working on recognizing object classes in images using neuronal nets so I could make classifiers for cats, dogs... using Imagenet and some Conv nets famous architectures but my problems is if I had an image that contain a human and a cat and a car how can I detect and recognize 3 of them?
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
It falls under the multi label object detection problem. There have been lots of advancements done in this field and you should definitely look at implementations like :
- Yolonet: https://pjreddie.com/darknet/yolo/
- Squeezenet: http://songhan.github.io/SqueezeNet-Deep-Compression/
