CODEWITHSUNDEEP
neural-networkdeep-learningcaffe
Deven
Deven

Reputation: 617

Epoch size (in terms of iterations) with data augmentation caffe

Suppose if one has training examples, and his batch size is 500, then it will take 2 iterations to complete 1 epoch. Now let's say I am using the caffe framework's on the fly data-augmentation, i.e; 10 crops per example.
My question is will the epoch size will still be 2 iterations as in the above examples or become 2*10 = 20?

Upvotes: 2

Views: 2286

Answers (1)

Shai
Shai

Reputation: 114786

An epoch is the the number of iterations it takes to go over the training data once. Since you augment your data, it will take you 10 times more iterations to complete one pass over the training data. Hence 1 epoch = 2*10 iterations now.

Upvotes: 4

Related Questions