You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
... the proposed architecture allows for resizing an image to any target size and aspect ratio.
So the Resizer should handle input image with any aspect ratio.
In spite of that, the Resizer implementation (interpolation) seems to assume the input image is square (or, only handle uniform-scale resize: e.g. (512, 256) -> (256, 128)).
The current implementation interpolates by specifying scale_factor, though I think it's more useful to specify the output image size and calculate scale factor automatically.
The reference code:
# current implementationself.interpolate=partial(F.interpolate,
scale_factor=self.scale_factor,
mode=self.interpolate_mode,
align_corners=False,
recompute_scale_factor=False)
The original paper says:
So the Resizer should handle input image with any aspect ratio.
In spite of that, the Resizer implementation (interpolation) seems to assume the input image is square (or, only handle uniform-scale resize: e.g. (512, 256) -> (256, 128)).
The current implementation interpolates by specifying
scale_factor
, though I think it's more useful to specify the output image size and calculate scale factor automatically.The reference code:
c.f. https://github.com/KushajveerSingh/resize_network_cv/blob/main/src/models/resizer.py#L56-L60
The text was updated successfully, but these errors were encountered: