I followed a tutorial on neural network model evaluation using cross-validation with code: # Multiclass Classification with the Iris Flowers Dataset import numpy import pandas from keras.models import Sequential from keras.layers import Dense from keras.wrappers.scikit_learn import KerasClassifier from keras.utils import np_utils from sklearn.model_selection import cross_val_score from sklearn.model_selection import KFold from sklearn.preprocessing import LabelEncoder from sklearn.pipeline import Pipeline # fix random seed for reproducibility seed = 7 numpy.random.seed(seed) # load dataset dataframe = pandas.read_csv("/content/drive/My Drive/iris.data", header=None) dataset = dataframe.values X = dataset[:,0:4].astype(float) Y = dataset[:,4] # encode class values as integers encoder = LabelEncoder() encoder.fit(Y) encoded_Y = encoder.transform(Y) # convert integers to dummy variables (i.e. one hot encoded) dummy_y = np_utils.to_categorical(encoded_Y) # define baseline model def baseline_model(): # create model model = Sequential() model.add(Dense(4, input_dim=4, activation="relu", kernel_initializer="normal")) model.add(Dense(3, activation="sigmoid", kernel_initializer="normal")) # Compile model model.compile(loss= 'categorical_crossentropy' , optimizer= 'adam' , metrics=[ 'accuracy' ]) return model estimator = KerasClassifier(build_fn=baseline_model, nb_epoch=200, batch_size=5, verbose=0) kfold = KFold(n_splits=10, shuffle=True, random_state=seed) results = cross_val_score(estimator, X, dummy_y, cv=kfold) print("Accuracy: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100)) The accuracy was supposed to be around 95.33% (4.27%) but I got ~Accuracy: 34.00% (13.15%) on a few attempts. The model code seems exactly the same. I downloaded the data from here as instructed. What could go wrong? Continue reading...
