0

From here and other sources TotalIteration = TotalExamples/Batchsize * Epochs. I have a CNN with 54 layers in total for 36000 examples, Batchsize of 12 and 3 Epochs. From the formula my Iteration is supposed to be 9000 but from the training-ui I am getting 3x9000 = 27000 at the end. Tried a smaller dataset with the formula again lo and behold it's 3 times whatever the calculation was for the total iteration.

Don't understand where the 3 is coming from or is it because my images have 3 channels(RGB) so it's seeing each channel as an example(wonder why if this is the case, since CNNs are supposed to consume data in volumes)

linker
  • 821
  • 1
  • 8
  • 20
  • How exactly are you running your training? Can you share your training code? – Paul Dubs Mar 12 '20 at 08:17
  • Sorry I forgot to add: the network has two output layers and then data is fed via a multi-dataset-iterator with 3 readers added; I see where the 3 is coming from now, also realised I have 3 training folders(36000 items each) for the multi-dataset-iterator but would that not mean during training that the iterator is feeding data 1 example at a time in a batch as per 12x1 instead of 12x3 from the 3 folders for a complete pass(the 1st folder contains images, the 2nd and 3rd folders contain different corresponding image data) – linker Mar 13 '20 at 12:43
  • or Does this mean that the network doesn't see a single multi-dataset from the iterator as 1 example but 3? – linker Mar 13 '20 at 12:43

0 Answers0