2 details questions about stn-ocr HOT 5 CLOSED

N is the number of stn matrix in paper.

from stn-ocr.

Hi,

N does not change during training. It is set to the maximum amount of text regions you want your network to extract. Naturally, it will happen that some words are shorter than N. IN this case you must make sure that the these extra timesteps are labelled with the blank label, so that the network learns to predict the correct number of characters/words in the image.

Let's have a look at your example: Let's assume the 16 is in the top-left corner of the image and the 18 is in the bottom-right corner of the image. Since we always assumed that we read from left to right and top to bottom, we would say that the first label is 16 and the second label is 18. With this way of defining our labels, we tell the network to put the first prediction always close to the most top-left word and all other predictions following the reading direction.

from stn-ocr.

@Bartzi，thanks for your reply. Maybe I didn`t explain my question 1 clearly. for question 2，I got it. About the N，it seems that you explain it as CTC loss. My question is that ，for example，now the N is set as 3，it means we can get 3 prediction text regions. if the number of ground truth labels is only 2，like “16” and "18" as above，you mean that we must make sure the label of extra prediction region is blank？Am I right？

from stn-ocr.

Yes, that's it!

from stn-ocr.

@Bartzi Thanks a lot ! Hope everything goes well with you !

from stn-ocr.