I am working on a computer vision project and encountered the following problem:
Images were labeled directly, and after that, a JSON file with the coordinates was generated. I managed to extract the necessary coordinates from the JSON file, but I am unable to place these coordinates on the JPG image to perform CNN training.
Is there any way to accomplish this process?
I have done some research but haven’t found a way to accomplish this task yet. I also tried to follow the steps from this video: https://www.youtube.com/watch?v=SQng3eIEw-k&t=1133s. I made the necessary adaptations, but it still didn’t work.
Diogo Rezende is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.