tensorflow - Change constant in tensoflow session while looping -

how can change tensorflow constant inside session for loop.
learner , wondering how update in loop

---

import tensorflow tf import numpy np  loopercount = 10  data = np.random.randint(2, size=loopercount) x = tf.constant(data, name='x')  y = tf.variable((5 * (x * x)) - (3 * x) + 15, name="y") model = tf.initialize_all_variables()  tf.session() sess:     in range(loopercount):         sess.run(model)         data = np.random.randint(2, size=loopercount)         x = tf.constant(data, name='x')         avg = np.average(sess.run(y))         print "avg - {}, sess - {}".format(avg, sess.run(y)) 

---

updated working code

import tensorflow tf import numpy np  loopercount = 10  x = tf.placeholder("float", loopercount) y = (5 * (x * x)) - (3 * x) + 15  tf.session() sess:     in range(loopercount):         data = np.random.randint(10, size=loopercount)         result_y = sess.run(y, feed_dict={x: data})         avg = np.average(result_y)         print "avg - {:10} valy - {:10}".format("{:.2f}".format(avg), result_y) 

in tensorflow, "constant" means that: once set it, can't change it. change value tensorflow program uses in loop, have 2 main choices: (1) using tf.placeholder() feed in value, or (2) using tf.variable store value between steps, , tf.variable.assign() update it.

option 1 easier. here's example of how use implement program using placeholder:

import tensorflow tf import numpy np  loopercount = 10  data = np.random.randint(2, size=loopercount) x = tf.placeholder(tf.float64, shape=[2], name="x")  y = tf.variable((5 * (x * x)) - (3 * x) + 15, name="y") init_op = tf.initialize_all_variables()  tf.session() sess:     sess.run(init_op)           in range(loopercount):         data = np.random.randint(2, size=loopercount)         avg = np.average(sess.run(y, feed_dict={x: data}))         print "avg - {}, sess - {}".format(avg, sess.run(y, feed_dict={x: data}))