What is the difference between these two situations? are they the same ?

#1 : train a model 20 epochs on the whole dataset

#2 : divide dataset into n-parts then train the model 20 epochs on each part

20 is a random number just for clarification. do we get the same result (accuracy) between these two situations? and why ?

Side note: this question was raised in my mind when I faced a problem: dataset is bigger than the storage space. So I want to divide it into 4 parts and train the model on each part. But does this effect on accuracy ? does this method of training is correct ?


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.