cross_entropy = tf.reduce_mean(
-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
W_grad = tf.gradients(cross_entropy, [W])[0]
train_step = tf.assign(W, W - 0.5 * W_grad)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# get the mnist dataset (use tensorflow here)
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# train
for _ in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
# eval
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
ans = sess.run(accuracy,
feed_dict={
x: mnist.test.images,
y_: mnist.test.labels
})
print("Accuracy: %.3f" % ans)
assert ans >= 0.87
# Training cycle
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples / batch_size)
# Loop over all batches
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost],
feed_dict={
x: batch_x,
y: batch_y
})
#print _
# Compute average loss
avg_cost += c / total_batch
# Display logs per epoch step
if epoch % display_step == 0:
print("Epoch:", '%04d' % (epoch+1), "cost=", \
"{:.9f}".format(avg_cost))
print("Optimization Finished!")
# Test model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# Calculate accuracy
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
ans = accuracy.eval({x: mnist.test.images, y: mnist.test.labels})
print("Accuracy: %.3f" % ans)
assert ans >= 0.80