YOLOV8 GRAD-CAM
Author: ElfMerveCreated Jul 31, 2024Updated Mar 28, 2025
In the grad-cam code for Yolov8, why is the layer specified as 5 layers? In the code; 'layer': [10, 12, 14, 16, 18]) Normally it is processed according to the last convulusion layer. What are the meanings of these given layers? Why is more than one layer used?
Source: z1069614715/objectdetection_script