aster.pytorch
aster.pytorch copied to clipboard
Surprising behaviour of trained model during tesing on single image.
I have trained aster on Price tags data. And got an Test (lmdb data ) accuracy of 60 percent. But when i am testing the saved checkpoint on single image. It is predicting like. l((((((((((l((((. For all images.
Why it is so ?
Please Help !!
Thanks for you response in advance.
Is the right checkpoint loaded? And do you use the given code for testing or rewrite a new one?