eval() and run() in tensorflow

Question

I'm referring to Deep MNIST for Experts tutorial given by the tensorflow. I have a problem in Train and Evaluate part of that tutorial. There they have given a sample code as follows.

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print("test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images,
                       y_: mnist.test.labels, keep_prob: 1.0}))

So in these code segment they have used accuracy.eval() at one time. And other time train_step.run(). As I know of both of them are tensor variables.

And in some cases, I have seen like

sess.run(variable, feed_dict)

So my question is what are the differences between these 3 implementations. And how can I know what to use when..?

Thank You!!

Answer 1

If you have only one default session, they are basically the same.

From https://github.com/tensorflow/tensorflow/blob/v1.12.0/tensorflow/python/framework/ops.py#L2351:

op.run() is a shortcut for calling tf.get_default_session().run(op)

From https://github.com/tensorflow/tensorflow/blob/v1.12.0/tensorflow/python/framework/ops.py#L691:

t.eval() is a shortcut for calling tf.get_default_session().run(t)

Difference between Tensor and Operation:

Tensor: https://www.tensorflow.org/api_docs/python/tf/Tensor

Operation: https://www.tensorflow.org/api_docs/python/tf/Operation

Note: the Tensor class will be replaced by Output in the future. Currently these two are aliases for each other.