To be more specific I have a dataset of 2400 images with unbalanced classes, 1 object per image and sometimes some objects are repeated along the dataset but in a different position and rotation of the object.

So the problem is, will the neural network trained on this data set recognize objects in different scenarios?


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.