search

solivr / tf-crnn

TensorFlow convolutional recurrent neural network (CRNN) for text recognition
GNU General Public License v3.0
292 stars 98 forks source link

Frozen a model issues #28

Closed zdnet closed 5 years ago

zdnet commented 6 years ago

Hi, thanks for your repo. I want to export a frozen model after trained, but how to set the input & output node name? i tried output_node_names = "code2str_conversion/predicted_words" but seems input "images" is not in graph: ValueError: Attempted to map inputs that were not found in graph_def: [images:0]

Could you please advice how can i export a frozen model?

Thanks.

JcmeLs commented 6 years ago

I have the same question. And I use input_dict, output_dict = _signature_def_to_tensors (loaded_model.signature_def ['predictions']) to get the name of the input and output nodes. It return input node name is Placeholder: 0. However, I did not find this input in the graph when checkpoint was restored

solivr commented 5 years ago

Hello, the updated version of the code uses tf.keras, so this should be easier to deal with.