Closed AdarshMJ closed 6 years ago
this repository implements word recognition only.
Images of sentences are much larger, therefore the neural network size has to be increased. I give some hints how to do this in this article section 2, however, I do not provide any code.
The corpus.txt file looks like this - corpus.txt
But the corresponding words.txt looks like this words.txt
The words.txt file in this case has each word of the corpus.txt separately defined, instead of whole sentences, how to achieve this?