Closed LinJM closed 3 months ago
As the title asks, how does this model process the coordinate information in object detection? Is it normalized to 0 to 1 ? Is it necessary to refer to the input resolution of the Tiny module?
After normalizing to 0 to 1, the values expanded by 1000 times, as stated in the report.
thanks
As the title asks, how does this model process the coordinate information in object detection? Is it normalized to 0 to 1 ? Is it necessary to refer to the input resolution of the Tiny module?