Tensorflow (1)

'tf.placeholder' or 'tf.Variable'

The difference is that with tf.Variable you have to provide an initial value when you declare it. With tf.placeholder you don't have to provide an initial value and you can specify it at run time with the feed_dict argument inside Session.run

'Session.run()' or 'Tensor.eval()'

If you have a Tensor t, calling t.eval() is equivalent to calling tf.get_default_session().run(t).

You can make a session the default as follows:

t = tf.constant(42.0)
sess = tf.Session()

with sess.as_default():   # or `with sess:` to close on exit
    assert sess is tf.get_default_session()
    assert t.eval() == sess.run(t)

The most important different is that you can use sess.run() to fetch the values of many tensors in the same step:

t = tf.constant(42.0)
u = tf.constant(37.0)
tu = tf.mul(t, u)
ut = tf.mul(u, t)
with sess.as_default():
   tu.eval()  # runs one step
   ut.eval()  # runs one step
   sess.run([tu, ut])  # runs a single step

Note that each call to eval and run will execute the whole graph from scratch. To cache the result of a computation, assign it to a tf.Variable.