How does keras calculate accuracy for multi label classification?

Question

I am using this code for a multilabel problem classification.

from __future__ import print_function

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Embedding
from keras.layers import LSTM
from keras.models import Model
from keras.datasets import imdb

max_features = len(vocabDic)
maxlen = 500  # cut texts after this number of words (among top max_features most common words)
batch_size = 32

train_set = sequence.pad_sequences(train_set, maxlen=maxlen)
test_set = sequence.pad_sequences(test_set, maxlen=maxlen)

print('train_set shape:', train_set.shape)
print('test_set shape:', test_set.shape)

print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 128))
model.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(90, activation='sigmoid'))

# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

print('Train...')
model.fit(train_set, train_labels,
          batch_size=batch_size,
          epochs=15,
          validation_data=(test_set, test_labels))
score, acc = model.evaluate(test_set, test_labels,
                            batch_size=batch_size)
print('Test score:', score)
print('Test accuracy:', acc)

My problem is there are 90 classes and the accuracy is too high from the second epoch. I suspect keras is computing something incorrectly. Any clues?

Edit: I calculated the total recall of the model. It is barely 5%( 5 times better than random). Is it a normal behavior for such a problem?

Answer 1

Why are you using binary_crossentropy? You should be using categorical_crossentropy. However, if you insist on using binary_crossentropy change your metric to metrics=['binary_accuracy', 'categorical_accuracy'] (this will display both accuracies).

Answer 2

I have answered a similar question here.

Your problem is that Accuracy is not the right metric for multi-label tasks. Try something different like AUC, precision, recall, accuracy@k, precision@recall. The choice of binary_crossentropy is correct since you are predicting each label independently.