A-CRNN-model-for-Text-Recognition-in-Keras
A-CRNN-model-for-Text-Recognition-in-Keras copied to clipboard
ignore_longer_outputs_than_inputs should be set to True
While trying to train the model on IAM dataset, an error would pop up about the output size mismatch with 31 hidden layers of BiLSTM in ctc_loss function. For that in tensorflow_core under https://www.tensorflow.org/api_docs/python/tf/nn/ctc_loss function set ignore_longer_outputs_than_inputs to True.