opt6.py

def RosenbrockOpt(optimizer,MAX_EPOCHS = 4000, MAX_STEP = 100):
	'''
	returns distance of each step*MAX_STEP w.r.t minimum (1,1)
	'''
	x1_data = tf.Variable(initial_value=tf.random_uniform([1], minval=-3, maxval=3,seed=0),name='x1')
	x2_data = tf.Variable(initial_value=tf.random_uniform([1], minval=-3, maxval=3,seed=1), name='x2')

	y = tf.add(tf.pow(tf.subtract(1.0, x1_data), 2.0),
	tf.multiply(100.0, tf.pow(tf.subtract(x2_data, tf.pow(x1_data, 2.0)), 2.0)), 'y')

	global_step_tensor = tf.Variable(0, trainable=False, name='global_step')

	train = optimizer.minimize(y,global_step=global_step_tensor)

	sess = tf.Session()

	init = tf.global_variables_initializer()#tf.initialize_all_variables()
	sess.run(init)

	minx = 1.0
	miny = 1.0

	distance = []
	xx_ = sess.run(x1_data)
	yy_ = sess.run(x2_data)
	print(0,xx_,yy_,np.sqrt((minx-xx_)**2+(miny-yy_)**2))
	for step in range(MAX_EPOCHS):
	  _, xx_, yy_, zz_ = sess.run([train,x1_data,x2_data,y])
	  if step % MAX_STEP == 0:
		 print(step+1, xx_,yy_, zz_)
		 distance += [ np.sqrt((minx-xx_)**2+(miny-yy_)**2)]
	sess.close()
	return distance

Hi, thanks for the interesting tutorial and example on how to implement an optimizer in Tensorflow. However, I was unable to run the example you provided after calling it as follows:
RosenbrockOpt(optimizer,MAX_EPOCHS = 4000, MAX_STEP = 100)
I got the following message:
that there is not 'minimize' function in the Tensorflow package:
AttributeError: module 'tensorflow.python.training.optimizer' has no attribute 'minimize'
The full error is:
in RosenbrockOpt(optimizer, MAX_EPOCHS, MAX_STEP)
11 global_step_tensor = tf.Variable(0, trainable=False, name='global_step')
12
---> 13 train = optimizer.minimize(y,global_step=global_step_tensor)
14
15 sess = tf.Session()

AttributeError: module 'tensorflow.python.training.optimizer' has no attribute 'minimize'
I am able to find out why this happens. How did you run the example?