I followed the tutorial to finetune an object-detection network.
My images are initially 2048x2048 and are rescaled to 512x512 during training (function
data_shape=512) , and also for detection (using
gcv.data.transforms.presets.ssd.load_test with parameter
I can use my fine-tuned network to detect my objects in new 2048x2048 squared images.
I tried then run the detection on cropped images (1466x442) but then it completely fails !
load_test function returns an image of dimensions 1024x309 with those rectangular cropped images.
I though the data augmentation used during the training would make the trained network scale-invariant to some extent, or at least such that it stills perform well on cropped images.