Hi @hellochick , I wonder if the implementation of inerp layer is similar to the original implementation ? The current function does not have conditional statements to check if only shrink or zoom is given, also the shrink implementation doesn't seem to reduce the dimension. Is there a reason for this ?
The original version of interp layer can shrink the image by just setting the parameter of (s_factor, z_factor) to (0.5, 1). Then it would downsample the original image to 1/2 resolutions
Hi @hellochick , I wonder if the implementation of inerp layer is similar to the original implementation ? The current function does not have conditional statements to check if only shrink or zoom is given, also the shrink implementation doesn't seem to reduce the dimension. Is there a reason for this ?
Possible change: