Explore Courses Blog Tutorials Interview Questions
0 votes
in Machine Learning by (33.1k points)

I am training a simple model in keras for the NLP task with the following code. Variable names are self-explanatory for train, test and validation set. This dataset has 19 classes so the final layer of the network has 19 outputs. Labels are also one-hot encoded.

nb_classes = 19

model1 = Sequential()






model1.add(LSTM(num_lstm, dropout=rate_drop_lstm, recurrent_dropout=rate_drop_lstm))



model1.add(Dense(num_dense, activation=act))



model1.add(Dense(nb_classes, activation = 'sigmoid'))

model1.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

#One hot encode all labels

ytrain_enc = np_utils.to_categorical(train_labels)

yval_enc = np_utils.to_categorical(val_labels)

ytestenc = np_utils.to_categorical(test_labels), ytrain_enc,

             validation_data=(val_data, yval_enc),





After the first epoch, this gives me these outputs.

Epoch 1/200

216632/216632 [==============================] - 2442s - loss: 0.1427 - acc: 0.9443 - val_loss: 0.0526 - val_acc: 0.9826

I evaluate my model on the testing dataset and this also shows me accuracy around 0.98.

model1.evaluate(test_data, y = ytestenc, batch_size=384, verbose=1)

The labels are one-hot encoded, so I need a prediction vector of classes so that I can generate confusion matrix, etc.

PREDICTED_CLASSES = model1.predict_classes(test_data, batch_size=384, verbose=1)

temp = sum(test_labels == PREDICTED_CLASSES)



This shows that total predicted classes were 83% accurate however model1.evaluate shows 98% accuracy!! What am I doing wrong here? Is my loss function okay with categorical class labels? Is my choice of sigmoid activation function for the prediction layer okay? or there is a difference in the way keras evaluates a model? Please suggest what can be wrong. This is my first try to make a deep model so I don't have much understanding of what's wrong here.

1 Answer

0 votes
by (33.1k points)

It seems like metrics=['accuracy'] method. calculates accuracy automatically from cost function. So using binary_crossentropy shows binary accuracy, not categorical accuracy. Using categorical_crossentropy automatically switches to categorical accuracy and now it is the same as calculated manually using model1.predict().

One can get both categorical and binary accuracy by using :

metrics=['binary_accuracy', 'categorical_accuracy']

Hope this answer helps you! Undergo the NLP Training for more details. Since this is somewhat related to Machine Learning, one can always go through the Machine Learning Tutorial.

Browse Categories