I would like to ask you about how I should deal with the images I have. They are really large. They have this shape: (3000, 4000, 3).

I'm working on a multilabel classification model.

And I want to know if it's wise to slice the images into equal tiles (using image_slicer) and to feed them to the model as well as resize the original images to the requisite input size of the model and feed those too.

So the training set would be: resized_original_images + tiles_of_original_image

Thank you

  • $\begingroup$ If you were to scale your images down, would you lose a lot of information? $\endgroup$ – Nischal Hp Nov 27 '19 at 15:56
  • $\begingroup$ @NishalHp The resolution isn't great. They're underwater images of algae, seagrass, corals etc. So the quality is bad. I'm planning to do a dehazing enhancement technique to make it better. To answer your question, I'm sure that going from the original size to say 256x256x3 would incur loss of details. $\endgroup$ – user Nov 27 '19 at 16:50

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.