I have a question about “randomize_input_shape_period” parameter mentioned in YOLOV3 documentation:
As far as I know, all input images should have the same size. But according to this parameter, the height and width of the input images change randomly per K batches.
Is the same size of the input images violated?
For this parameter, it is similar to
random=1 - randomly resizes network for each 10 iterations from
1.4 (data augmentation parameter is used only from the last layer)
CFG Parameters in the different layers · AlexeyAB/darknet Wiki · GitHub
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.