I found that when the transformed coordinates exceeding the image size,the size of the label will be (0,2),
Running the lr_find () function at this point will get the following error:
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 1 and 0 in dimension 1 at /pytorch/aten/src/TH/generic/THTensor.cpp:711
I have an idea when found the size of the label is (0,2),then discard the current augmented image and get a new augmented image again.But I don’t know how to write code to achieve.How do I fix this?