search

Bartzi / stn-ocr

Code for the paper STN-OCR: A single Neural Network for Text Detection and Text Recognition
https://arxiv.org/abs/1707.08831
GNU General Public License v3.0
499 stars 137 forks source link

train original svhn datasets #33

Open fycfycfyc opened 3 years ago

fycfycfyc commented 3 years ago

Excuse me: I noticed that your code gives the training steps of the model on the two variant data sets of svhn, but the training steps of the model on the original svhn data set are not given. If you want the model to be trained on the original svhn data set, how should the original svhn data set be preprocessed? For example, how big should the svhn data set be resized? Looking forward to your reply.Thank you very much!

Bartzi commented 3 years ago

Hmm, that's a very good question to be honest. I can't remember entirely. However, my guess is that we just used the text recognition training script. Recognizing Characters on already cropped SVHN numbers is the same as recognizing text.