def export_to_tf(model, to): model_builder = tf.saved_model.builder.SavedModelBuilder(to) inputs = {'input': tf.saved_model.utils.build_tensor_info(model.input)} outputs = { 'earnings': tf.saved_model.utils.build_tensor_info(model.output) } signature_def = tf.saved_model.signature_def_utils.build_signature_def( inputs=inputs, outputs=outputs, method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME) model_builder.add_meta_graph_and_variables( K.get_session(), tags=[tf.saved_model.tag_constants.SERVING], signature_def_map={ tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: signature_def }) model_builder.save()
# Create a Tensorboard Logger logger = TensorBoard(log_dir=logs, histogram_freq=5, write_graph=True) history = model.fit(X_train, Y_train, epochs=40, batch_size=15, validation_data=(X_test, Y_test), verbose=2, callbacks=[logger]) model_builder = tf.saved_model.builder.SavedModelBuilder( "../exported_model{}".format(modelType)) inputs = {'input': tf.saved_model.utils.build_tensor_info(model.input)} outputs = {'motion': tf.saved_model.utils.build_tensor_info(model.output)} signature_def = tf.saved_model.signature_def_utils.build_signature_def( inputs=inputs, outputs=outputs, method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME) model_builder.add_meta_graph_and_variables( K.get_session(), tags=[tf.saved_model.tag_constants.SERVING], signature_def_map={ tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: signature_def }) model_builder.save()