Demo phase about crnn-pytorch

[Holmeyoung]

Hi, yeah, it can recognize ABC!

1. We can consider that if we need to give all the condition, then when len(alphabet) = 3000 and the txt_len = 10, we need 3000^10 sample. Of course it's impossible.

2. You can think it as splited, whitch menas AAA can be splited as A, A, A, so as B, C... as for the reason why we need more data, it's we need the net to learn the right feature of the alphabet and diff different alphabets.
   Look at the encode function, you can see the labels are splited treated

   def encode(self, text):
       length = []
       result = []
       for item in text:            
           item = item.decode('utf-8','strict')
           length.append(len(item))
           for char in item:
               index = self.dict[char]
               result.append(index)
               
       text = result
       return (torch.IntTensor(text), torch.IntTensor(length))

[Holmeyoung]

Yes, you are right!

[mariembenslama]

I see, so that's the work of CNN and RNN combined together, right?