my code snippet is below [TIM图片20210919214656] [TIM图片20210919214702] Now ,the img ,gt do different RandomResizedCrop. But I want they do the same, because the img and gt must be correspond. How should I modify the code?

https://discuss.pytorch.org/t/torchvision-transfors-how-to-perform-identical-transform-on-both-image-and-target/10606 Read the topic above, and then read some Github issues. Now, I think the best solution is to write own transform(take both image and target as arguments). For example, my initial…

How to get the same RandomResizedCrop result of img and gt

vision

arya47 (Aryaman) September 20, 2021, 12:33am 2

This thread might be relevant