Icon

20200616r Pikairos Keras metrics export

# variable name of the input network: input_network (here a Dummy model)# variable name of the input table: input_table (here a Dummy input table)# variable name of the output table: output_table (here a data set)# https://en.wikipedia.org/wiki/Pandasfrom pandas import DataFramefrom keras.models import Sequentialfrom keras.layers.core import Dense, Activationfrom keras.optimizers import SGDfrom keras.utils import np_utils# https://en.wikipedia.org/wiki/NumPyimport numpy as np# X_test = input_table['X_test']number_of_rows = X_test.shape[0]print( number_of_rows)X_test = np.asarray( X_test)X_test = np.concatenate( X_test, axis=0 )print( X_test.shape)X_test = X_test.reshape( number_of_rows, 784) print( "Shape of Input Data: ", X_test.shape)# Convert Class to Categorical ArrayNB_CLASSES = 10Y_test = np_utils.to_categorical( input_table['class'], NB_CLASSES)OPTIMIZER = SGD() # SGD optimizerinput_network.compile(loss='categorical_crossentropy', optimizer=OPTIMIZER, metrics=['accuracy'])input_network.summary()VERBOSE = 1score = input_network.evaluate(X_test, Y_test, verbose=VERBOSE)print("\nTest score:", score[0])print('Test accuracy:', score[1])flow_variables['Test score'] = score[0]flow_variables['Test Accuracy'] = score[1]##############Prediction = input_network.predict(X_test, verbose=VERBOSE)print( "Shape of Prediction: ", Prediction.shape) output_table = DataFrame(Prediction) Neural NetworkInput + Dense + SoftMaximplemented usingKERASExtract MetricsMNIST Imagescan be extracted fromKERAS librarydirectlyCollect all input columnsinto a single columnof type listDL PythonNetwork Creator DL Python NetworkExecutor Extract MNISTdata from KERAS Create CollectionColumn # variable name of the input network: input_network (here a Dummy model)# variable name of the input table: input_table (here a Dummy input table)# variable name of the output table: output_table (here a data set)# https://en.wikipedia.org/wiki/Pandasfrom pandas import DataFramefrom keras.models import Sequentialfrom keras.layers.core import Dense, Activationfrom keras.optimizers import SGDfrom keras.utils import np_utils# https://en.wikipedia.org/wiki/NumPyimport numpy as np# X_test = input_table['X_test']number_of_rows = X_test.shape[0]print( number_of_rows)X_test = np.asarray( X_test)X_test = np.concatenate( X_test, axis=0 )print( X_test.shape)X_test = X_test.reshape( number_of_rows, 784) print( "Shape of Input Data: ", X_test.shape)# Convert Class to Categorical ArrayNB_CLASSES = 10Y_test = np_utils.to_categorical( input_table['class'], NB_CLASSES)OPTIMIZER = SGD() # SGD optimizerinput_network.compile(loss='categorical_crossentropy', optimizer=OPTIMIZER, metrics=['accuracy'])input_network.summary()VERBOSE = 1score = input_network.evaluate(X_test, Y_test, verbose=VERBOSE)print("\nTest score:", score[0])print('Test accuracy:', score[1])flow_variables['Test score'] = score[0]flow_variables['Test Accuracy'] = score[1]##############Prediction = input_network.predict(X_test, verbose=VERBOSE)print( "Shape of Prediction: ", Prediction.shape) output_table = DataFrame(Prediction) Neural NetworkInput + Dense + SoftMaximplemented usingKERASExtract MetricsMNIST Imagescan be extracted fromKERAS librarydirectlyCollect all input columnsinto a single columnof type listDL PythonNetwork Creator DL Python NetworkExecutor Extract MNISTdata from KERAS Create CollectionColumn

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: Molina
Created at: 2020-06-16
On NodePit since: 2022-02-06
Last update: 2024-05-02
Created with KNIME version: v4.0.2

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!