I’m doing a task of semantic segmentation:
I have trained a fully-convolutional CNN (like Tiramisu) using a segment_generator() on random slices of 512,512 (for example) without resize.
I would now like to do
model.predict on the entire image and considering two approaches:
- Since this is a fully convolutional CNN - I can input the entire image (let’s say 1920x1280) and get a prediction
- Use a sliding window loop
For some reason, when using a sliding window I am getting significantly better results (dice 0.996 vs 0.993).
Any ideas why I’m experiencing this?