Modifying the model for multi object localization in an image

[farshadopencv]

Hi. thanks for your amazing work. this model works very nice. But i have a question. when i feed the model with an image with two or three cats, I have only one box and its accuracy is very low. How can I modify the model for multi detection? what parts of the train_model.py or evaluate_performance.py should be changed for that? Your response will be highly appreciated.

[lars76]

Hi, example_1 and example_2 only support single-object detection. If you want to modify these two examples, you need to look at papers like YOLO, SSD etc.

Alternatively, use example_3 it supports multiple objects. You only have to modify the grouping function in test.py. YOLO is basically like example_3, except that it uses regression and some other fancy stuff (stronger architecture, anchor boxes etc.).