x = tf.placeholder(tf.float32, [None, 784])

W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, W) + b)

y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

def train(data):
    global train_step, x, y
    trd = []

    # getting a letter from Option Menu
    l = dropVar.get()
    if l == 'a':
        trd = [1, 0, 0]
    # and so on

    sess.run(train_step, feed_dict={x: data, y_: trd})

def test(data):
    global x, y_, y
    trd = []

    # getting a letter from Option Menu
    l = dropVar.get()
    if l == 'a':
        trd = [1, 0, 0]
    # and so on

    correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print(sess.run(accuracy, feed_dict={x: data, y_: trd}))

    # data is an image converted into a vector