Faster R-CNN (frozen inference graph inception v2 based) execution time is same for 360p and 1080p. How is this possible?

Question

I just implemented Faster R-CNN (frozen inference graph inception v2 based) object detection model on Jetson TX2 with jetpack 4.2 and tensorflow version 1.14. The model was given an input frame of resolution 1080p and later 360p. Surprisingly, there was no change in execution time. What could possibly be the reason for this?

Answer 1

Faster R-CNN consists of 3 main blocks:

1. Base feature network (generates feature map from input image/frame),

2. Region proposal network (generates/proposes/selects interesting regions for final bounding box generation from anchors) and

3. Detection network (RPN) (classifies the region as background or foreground and refines bounding boxes).

Most of the complexities of Faster R-CNN lie in RPN and detection network and the RPN has a fixed input shape. Therefore, the execution time of the model is not affected significantly.