Tensorflow错误:ValueError:不支持任何值

时间:2018-03-10 23:05:21

标签: python python-3.x tensorflow

这是我的测试代码。但它无法运行。终端总是给我这个错误:

追踪(最近一次通话):   文件" desktop / test.py",第28行,in     loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices = [1]))   文件" /Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py" ;,第898行,在binary_op_wrapper中     y = ops.convert_to_tensor(y,dtype = x.dtype.base_dtype,name =" y")   文件" /Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py" ;,第932行,在convert_to_tensor中     as_ref = FALSE)   文件" /Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py",第1022行,在internal_convert_to_tensor中     ret = conversion_func(value,dtype = dtype,name = name,as_ref = as_ref)   文件" /Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py" ;,第233行,在_constant_tensor_conversion_function中     返回常量(v,dtype = dtype,name = name)   File" /Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py" ;,第212行,常量     value,dtype = dtype,shape = shape,verify_shape = verify_shape))   文件" /Users/sumeixu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py" ;,第401行,在make_tensor_proto中     提高ValueError("不支持任何值。") ValueError:不支持任何值。

请帮助。 Blew是我的代码。非常感谢你!

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}))

1 个答案:

答案 0 :(得分:2)

所以我运行了你的代码,在我修改了第一个函数中的缩进后,它运行得很好。如果我只是在你编写时复制粘贴它,我也会得到None错误(因为你没有从函数中返回任何内容)。所以只需解决缩进,就可以了!

要获得损失,您可以按如下方式获取值:

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