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?