Reputation: 8411
I've written the following quick program in tensorflow to print fibonacci numbers. Initial fib numbers are initialized as placeholders x1
and x2
However when I try to feed the value of the placeholders in session.run
it results in the error :
InvalidArgumentError: You must feed a value for placeholder tensor 'x2' with dtype int64 and shape [1]
Can you help me understand and fix the problem with my code?
import tensorflow as tf
session = tf.InteractiveSession()
import numpy as np
ones = tf.ones((1,))
n = 10
x1 = tf.placeholder(tf.int64, [1], name='x1')
x2 = tf.placeholder(tf.int64, [1], name='x2')
temp = tf.Variable(ones, name='temp')
tf.initialize_all_variables().run()
fib_nums = [x1, x2]
for i in range(100):
temp = x1 + x2
x1 = x2
x2 = temp
fib_nums.append(temp)
series = tf.stack(fib_nums)
print(np.ones(1).astype(np.int64))
session.run(series, feed_dict={x1:np.ones(1).astype(np.int64), x2:np.ones(1).astype(np.int64)})
print(series.eval())
Upvotes: 1
Views: 1304
Reputation: 3207
I think another variation is this using tf.identity.
y = tf.identity(x1)
y1 = tf.identity(x2)
fib_nums = [y, y1]
for i in range(100):
temp = y + y1
y = y1
y1 = temp
fib_nums.append(temp)
This placeholder modification issue is also discussed here
And this is one more way to get the series.
def cond(i, x_next, x_prev):
return x_next <= 100
def body( i, x_next, x_prev ):
nextinseries = x_next + x_prev
next = tf.Print(x_next, [x_next], message="Next is : ")
prev = tf.Print(x_prev, [x_prev], message="Previous is : ")
with tf.control_dependencies([nextinseries]):
prev = tf.identity( next )
return [i + 1, nextinseries , prev ]
sess = tf.Session()
sess.run(tf.global_variables_initializer())
sess.run(tf.while_loop(cond, body, [1, 1, 1]))
Upvotes: 1
Reputation: 59741
There are a couple of errors here. First, since you are reusing the Python names x1
and x2
, when you give them in the feed_dict
they no longer refer to the placeholders, but to the last results of the loop. So you should change your code so the keys that you give in feed_dict
are truly the placeholders. Second, you first call session.run
with the feed_dict
, which is correct, but then you call series.eval()
, which is essentially the same as the previous line, only you are not providing the feed_dict
in this case so it is not going to work. You do not really need to call series.eval()
, you can just take the value returned by session.run
. Your fixed program could look something like this:
import tensorflow as tf
session = tf.InteractiveSession()
import numpy as np
ones = tf.ones((1,))
n = 10
# Reserve these Python names for the placeholders
x1_ph = tf.placeholder(tf.int64, [1], name='x1')
x2_ph = tf.placeholder(tf.int64, [1], name='x2')
temp = tf.Variable(ones, name='temp')
tf.initialize_all_variables().run()
# Use placeholders as initial values in the iterations
x1, x2 = x1_ph, x2_ph
fib_nums = [x1, x2]
for i in range(100):
temp = x1 + x2
x1 = x2
x2 = temp
fib_nums.append(temp)
series = tf.stack(fib_nums)
print(np.ones(1).astype(np.int64))
# You can just give lists as inputs and TensorFlow will convert their type
series_val = sess.run(series, feed_dict={x1_ph: [1], x2_ph: [1]})
print(series_val)
Output:
[1]
[[ 1]
[ 1]
[ 2]
[ 3]
[ 5]
[ 8]
[ 13]
[ 21]
[ 34]
[ 55]
[ 89]
[ 144]
[ 233]
[ 377]
[ 610]
[ 987]
[ 1597]
[ 2584]
...
Upvotes: 2
Reputation: 7103
Just change tf.placeholder
to a tensor and it will work
x1 = tf.ones(dtype=tf.int64, shape=1, name='x1')
x2 = tf.ones(dtype=tf.int64, shape=1, name='x2')
Upvotes: 0