Closed NewUser626 closed 2 years ago
The images are first resized to the same size as was used during training. Then inference is performed on these images. The output masks are then resized to the same size of the original input image.
if input feature map is not a multiple of patch size, we interpolate it before unfolding operation.
Closing because of inactivity. Please feel free to re-open if the issue is not addressed.
I am confused what is the image size in test on segmentation task? 515x512 or just the same ratio with original image ? how to handle the problem if the feature map can not be divided by patch size 2x2?