Created
August 16, 2020 18:31
-
-
Save Justin-Heer/1de0c1c0e82621ef05a654978e2176e7 to your computer and use it in GitHub Desktop.
testing the model accuracy on the test set
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# load the weights for the optimal model | |
lstm_model.load_weights('biLSTM.h5') | |
# Converts a class vector (integers) to binary class matrix | |
# for use with categorical_crossentropy | |
# IMPORTANT for CATEGORICAL_CROSSENTROPY! | |
y_test = np_utils.to_categorical(y_test, 2) | |
# generator for validating the LSTM model | |
test_gen = generate_batch(X_test, y_test, batch_size, expected_frames) | |
# checks the models performance | |
accu_test = lstm_model.evaluate(test_gen, | |
steps=len(X_test) // batch_size, | |
verbose=1) | |
# print the test result | |
print(f'The test accuracy for this model is {accu_test[1] * 100:0.2f}%') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment