Loss and accuracy are 0 when using a neural network with a single output neuron tensorflow

I am writing a binary classifier, for a certain task and instead of using 2 neurons in the output layer I want to use just one with a sigmoid function, and basically output class 0 if it is lower than 0.5 and 1 otherwise.

The images are loaded, resized to 64x64 and flattened,to create facsimile of the problem). The code for data load will be present at the end. I create the placeholders.

x = tf.placeholder('float',[None, 64*64])
y = tf.placeholder('float',[None, 1])

and define the model as follows.

def create_model_linear(data):

    fcl1_desc = {'weights': weight_variable([4096,128]), 'biases': bias_variable([128])}
    fcl2_desc = {'weights': weight_variable([128,1]), 'biases': bias_variable([1])}

    fc1 = tf.nn.relu(tf.matmul(data, fcl1_desc['weights']) + fcl1_desc['biases'])
    fc2 = tf.nn.sigmoid(tf.matmul(fc1, fcl2_desc['weights']) + fcl2_desc['biases'])

    return fc2

the functions weight_variable and bias_variable simply return a tf.Variable() of given shape. (code for them is also in the end.)

Then I define the training function as follows.

def train(x, hm_epochs):
    prediction = create_model_linear(x)
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits  = prediction, labels = y) )
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
    batch_size = 100
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())

        for epoch in range(hm_epochs):
            epoch_loss = 0
            i = 0
            while i < len(train_x):
                start = i
                end = i + batch_size
                batch_x = train_x[start:end]
                batch_y = train_y[start:end]
                _, c = sess.run([optimizer, cost], feed_dict = {x:batch_x, y:batch_y})

                epoch_loss += c
                i+=batch_size

            print('Epoch', epoch+1, 'completed out of', hm_epochs,'loss:',epoch_loss)
        correct = tf.greater(prediction,[0.5])
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        i = 0
        acc = []
        while i < len(train_x):
            acc +=[accuracy.eval({x:train_x[i:i+1000], y:train_y[i:i + 1000]})]
            i+=1000
    print sum(acc)/len(acc)

the output of train(x, 10) is

('Epoch', 1, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 2, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 3, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 4, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 5, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 6, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 7, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 8, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 9, 'completed out of', 10, 'loss:', 0.0) ('Epoch', 10, 'completed out of', 10, 'loss:', 0.0)

0.0 What am I missing?

And here is the promised code for all the utility functions:

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def getLabel(wordlabel):
    if wordlabel == 'Class_A':
        return [1]
    elif wordlabel == 'Class_B':
        return [0]
    else:
        return -1

def loadImages(pathToImgs):
    images = []
    labels = []
    filenames = os.listdir(pathToImgs)
    imgCount = 0
    for i in tqdm(filenames): 
        wordlabel = i.split('_')[1]
        oneHotLabel = getLabel(wordlabel)
        img = cv2.imread(pathToImgs + i,cv2.IMREAD_GRAYSCALE)
        if oneHotLabel != -1 and type(img) is np.ndarray: 
            images += [cv2.resize(img,(64,64)).flatten()]
            labels += [oneHotLabel]
            imgCount+=1
    print imgCount
    return (images,labels)