Tensorflow error: ValueError: None values not supported

Question

This is my test code. But it could not run. Terminal always gave me this error:

Traceback (most recent call last):
File "desktop/test.py", line 28, in loss =tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1])).
File "/Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 898, in binary_op_wrapper y = ops.convert_to_tensor(y, dtype=x.dtype.base_dtype, name="y")
File "/Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 932, in convert_to_tensor as_ref=False)
File "/Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1022, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 233, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name)
File "/Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 212, in constant value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 401, in make_tensor_proto raise ValueError("None values not supported.").

ValueError: None values not supported.

Help please. Blew is my code. Thank you so much!

import tensorflow as tf 
import numpy as np 
import matplotlib.pyplot as plt

def add_layer(inputs,in_size,out_size,activation_function=None):
    Weights=tf.Variable(tf.random_normal([in_size,out_size]))
    biases=tf.Variable(tf.zeros([1,out_size])+0.1)
    Wx_Plus_b = tf.matmul(inputs,Weights)+biases

    if activation_function is None:
        outputs=Wx_Plus_b
    else:
            outputs=activation_function(Wx_Plus_b)
            return outputs

x_data = np.linspace(-1,1,300)[:,np.newaxis]
noise=np.random.normal(0,0.05,x_data.shape)
y_data=np.square(x_data)-0.5+noise

xs=tf.placeholder(tf.float32,[None,1])
ys=tf.placeholder(tf.float32,[None,1])

l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)

prediction=add_layer(l1,10,1,activation_function=None)

loss =tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))

train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

for i in range(1000):
    sess.run(train_step,feed_dict={xs:x_data,ys:y_data})

    if i%50==0:
        print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))

Tom · Accepted Answer · 2018-03-11 00:17:24Z

3

So I ran your code and It works just fine, after I fixed the indent in your first function. If I just copy paste it as you wrote it, I also get the None error (since you return nothing from the function). So just solve the indent and it should work!

To get the loss you can just fetch the value as follows:

loss_list = []
if i%50==0:
    my_loss = sess.run(loss,feed_dict={xs:x_data,ys:y_data})
    loss_list.append(my_loss)

edited Mar 11, 2018 at 0:17

answered Mar 10, 2018 at 23:22

Tom

2843 silver badges19 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Sue-May Xu Over a year ago

Thanks for letting me know this. I fixed the indent and no error came out. I actually wanted to show error decrease while I increase i from 1 to 1000. for i in range(1000): sess.run(train_step,feed_dict={xs:x_data,ys:y_data}) if i%50==0: print(sess.run(loss,feed_dict={xs:x_data,ys:y_data})). Any ideas on how to fix that?

Sue-May Xu Over a year ago

Does that work for you? It does not show anything in my terminal :/

Collectives™ on Stack Overflow

Tensorflow error: ValueError: None values not supported

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related