1 | initial version |
Train dataset for temp stage can not be filled. Branch training terminated.
I think it is normal (at least it is not critical). When I check the log I have had, I have the same message after the 18-stage and when I test the result learning file, it works (with very few false detection).
But I am not sure if the message
Train dataset for temp stage can not be filled.
is normal (there is no more negative data misclassified ?) or it means the training works but the negative pool of images is too poor.