I have one image,where top left corner of the image (784,448,3) is used for test image and remaining area is used for training where overlapping patches of size (112,112,3). I have trained my Unet model on training images, so i want predict my test image different size on trained model. Is it possible to predict different size of test image on my trained model? If not possible then what mechanism should i use?

  • $\begingroup$ Could you please share a sample Image. How you make sure that the training process doesn't touch the test image i.e. top left corner $\endgroup$ – 10xAI Jul 21 at 6:04

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.