CODEWITHSUNDEEP
python-3.xtensorfloweval
Akash Chandra
Akash Chandra

Reputation: 395

Unable to print tf.zeros in tensorflow

weights = tf.Variable(tf.truncated_normal([image_size * image_size, num_labels]))
biases = tf.Variable(tf.zeros([num_labels]))`

This is a part of the code I encountered to minimize loss using Gradient Descent in tensorflow. I understood what is going on and what tf.zeros is doing but when I tried to run the follwing code it showed an error::

 sess = tf.IntearctiveSession()
 tensor = tf.Variable(tf.zeros(shape=(10)))
 print(tensor.eval())
 sess.close()

An error occured in print(tensor.eval()). Can someone point out where I understood the things wrong?

Upvotes: 1

Views: 405

Answers (1)

scrpy
scrpy

Reputation: 1021

Looks like you forgot to initialize your variable(s). Try this:

sess = tf.IntearctiveSession()
tensor = tf.Variable(tf.zeros(shape=(10)))
sess.run(tf.global_variables_initializer())  # Now all variables are initialized
print(tensor.eval())
sess.close()

Upvotes: 1

Related Questions