While using torchvision.detection models with torch above or equal to 1.6, I am getting the following warning on each mask interpolation in GenericRCNNTransform:
UserWarning: The default behavior for interpolate/upsample with float scale_factor changed in 1.6.0 to align with other frameworks/libraries, and now uses scale_factor directly, instead of relying on the computed output size. If you wish to restore the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor changed "
So, I am being recommended to specify recompute_scale_factor=True but this is an internal torchvision object which get’s the warning and I am not supposed to edit the code