The container will also need to write the following output: Surgical Tools (Multiple 2D bounding boxes) to /output/surgical-tools.json

Category #2 – Surgical tool detection:  The output json file needs to be a dictionary containing the set of tools detected in each frame with its correspondent bounding box corners (x, y), again generating a single json file for each video like given below:

Here it's mentioned that the output json file should contain info about all frames of the video. So should the /output file have multiple json files for each frame or should it contain information of all frames in a single json file ? It would be good if you could share an example of the output file in this case.

Thanking you