cross_val_score with Keras
Make model def build_model(): X = tf.keras.layers.Input(shape=[28, 28, 1]) H = tf.keras.layers.Conv2D(64, kernel_size=5, padding='same', activation='swish')(X) H = tf.keras.layers.BatchNormalization()(H) H = tf.keras.layers.Conv2D(64, kernel_size=5, padding='same', activation='swish')(H) H = tf.keras.layers.MaxPool2D()(H) H = tf.keras.layers.Conv2D(64, kernel_size=3, padding='same', activation='..