Multilabel Text Classification using TensorFlow

Question

The text data is organized as vector with 20,000 elements, like [2, 1, 0, 0, 5, ...., 0]. i-th element indicates the frequency of the i-th word in a text.

The ground t

Answer 1

Change relu to sigmoid of output layer. Modify cross entropy loss to explicit mathematical formula of sigmoid cross entropy loss (explicit loss was working in my case/version of tensorflow )

import tensorflow as tf

# hidden Layer
class HiddenLayer(object):
    def __init__(self, input, n_in, n_out):
        self.input = input

        w_h = tf.Variable(tf.random_normal([n_in, n_out],mean = 0.0,stddev = 0.05))
        b_h = tf.Variable(tf.zeros([n_out]))

        self.w = w_h
        self.b = b_h
        self.params = [self.w, self.b]

    def output(self):
        linarg = tf.matmul(self.input, self.w) + self.b
        self.output = tf.nn.relu(linarg)

        return self.output

# output Layer
class OutputLayer(object):
    def __init__(self, input, n_in, n_out):
        self.input = input

        w_o = tf.Variable(tf.random_normal([n_in, n_out], mean = 0.0, stddev = 0.05))
        b_o = tf.Variable(tf.zeros([n_out]))

        self.w = w_o
        self.b = b_o
        self.params = [self.w, self.b]

    def output(self):
        linarg = tf.matmul(self.input, self.w) + self.b
        #changed relu to sigmoid
        self.output = tf.nn.sigmoid(linarg)

        return self.output

# model
def model():
    h_layer = HiddenLayer(input = x, n_in = 20000, n_out = 1000)
    o_layer = OutputLayer(input = h_layer.output(), n_in = 1000, n_out = 4000)

    # loss function
    out = o_layer.output()
    # modified cross entropy to explicit mathematical formula of sigmoid cross entropy loss
    cross_entropy = -tf.reduce_sum( (  (y_*tf.log(out + 1e-9)) + ((1-y_) * tf.log(1 - out + 1e-9)) )  , name='xentropy' )    

    # regularization
    l2 = (tf.nn.l2_loss(h_layer.w) + tf.nn.l2_loss(o_layer.w))
    lambda_2 = 0.01

    # compute loss
    loss = cross_entropy + lambda_2 * l2

    # compute accuracy for single label classification task
    correct_pred = tf.equal(tf.argmax(out, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, "float"))

    return loss, accuracy