implement function demo/images_demo.py

[alaa-shubbak]

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• I have read the FAQ documentation but cannot get the expected help.
• The bug has not been fixed in the latest version (master) or latest version (3.x).

💬 Describe the reimplementation questions

There is no error , i just want to know how can i use function demo/images_demo.py or any other functions in this repository to test my images of exited model and weight for only one and certain category , not for the 80 categories within coco dataset.

I try the function on my images , need to have only one category presented but it gave me all objects within the image that have been included in the 80 items in coco dataset.

how can i remove the other categories ,without pretrained or do transfer learning for my models?

thanks .

Environment

Expected results

No response

Additional information

No response

[sanbuphy]

You can write a script to obtain the image address by passing through the annotations.json.
In the annotations you can find the category_id and address.
if the category_id is you want, just recording address in new variable and detect it .