Tensorflow无法评估渐变(Tensorflow fails to evaluate gradients)

 当我尝试使用tensorflow的boolean_mask函数和渐变优化器（在带有Anaconda 3.5的Windows x64上的tensorflow版本0.12.1）时，我遇到了一个问题。 
 
import tensorflow as tf
import numpy as np

# Test data
x_dat = np.arange(1, 13).reshape(4, 3).astype(np.float32)
y_dat = np.arange(1, 9).reshape(4, 2).astype(np.float32) 
map_x_on_y = np.array([[True, False], [False, False], [ True, True]])

# Test data
x = tf.placeholder(tf.float32, [None, 3])
y_ = tf.placeholder(tf.float32, [None, 2])

# Model: Take the column product of the elements of x using the rows of               
# map_x_on_y as a filter. 
# The two columns of map_x_on_y give the two columns of y

transpose_of_x = tf.transpose(x)
fn = lambda t: tf.reduce_prod(tf.boolean_mask(transpose_of_x, t), axis=0)
y = tf.stack([fn(i) for i in tf.unstack(map_x_on_y, axis=1)])

# Train the model
sum_of_squared_errors = tf.reduce_mean(tf.square(y_-y)) 
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(sum_of_squared_errors)
init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)
    feed_dict ={x: x_dat, y_: y_dat} 
    for i in range(10):   
        sess.run([train_step], feed_dict)
 
 我收到以下错误消息： 
 
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-108-cc039c0c3ed9> in <module>()
    21 # Train the model
    22 sum_of_squared_errors = tf.reduce_mean(tf.square(y_-y))
    ---> 23 train_step =                 tf.train.GradientDescentOptimizer(0.1).minimize(sum_of_squared_errors)
    24 init = tf.global_variables_initializer()
    25 

C:\Anaconda3\lib\site-packages\tensorflow\python\training\optimizer.py in minimize(self, loss, global_step, var_list, gate_gradients, aggregation_method, colocate_gradients_with_ops, name, grad_loss)
    274           "No gradients provided for any variable, check your graph for ops"
    275           " that do not support gradients, between variables %s and loss %s." %
    --> 276           ([str(v) for _, v in grads_and_vars], loss))
    277 
    278     return self.apply_gradients(grads_and_vars, global_step=global_step,

    ValueError: No gradients provided for any variable, check your graph for        ops that do not support gradients, between variables ['Tensor("Variable/read:0", shape=(3, 10), dtype=bool)', 'Tensor("Variable_1/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_2/read:0", shape=(3, 10), dtype=bool)', 'Tensor("Variable_3/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_4/read:0", shape=(3, 10), dtype=float64)', 'Tensor("Variable_5/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_6/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_7/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_8/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_9/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_10/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_11/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_12/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_13/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_14/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_15/read:0", shape=(5, 3), dtype=int32)', 'Tensor("Variable_16/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_17/read:0", shape=(5, 3), dtype=int32)', 'Tensor("Variable_18/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_19/read:0", shape=(5, 3), dtype=float32)', 'Tensor("Variable_20/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_21/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_22/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_23/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_24/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_25/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_26/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_27/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_28/read:0", shape=(3, 2), dtype=float32)', 'Tensor("Variable_29/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_30/read:0", shape=(3, 2), dtype=float32)', 'Tensor("Variable_31/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_32/read:0", shape=(3, 2), dtype=float32)', 'Tensor("Variable_33/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_34/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_35/read:0", shape=(5, 3), dtype=float32)', 'Tensor("Variable_36/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_37/read:0", shape=(5, 3), dtype=float32)', 'Tensor("Variable_38/read:0", shape=(3, 2), dtype=bool)'] and loss Tensor("Mean_1:0", shape=(), dtype=float32).
 
 只使用变量时，该操作看起来很好： 
 
import tensorflow as tf
import numpy as np

x = tf.Variable(np.arange(1, 13).reshape(4, 3).astype(np.float32))
map_x_on_y = np.array([[True, False], [False, False], [ True, True]])

transpose_of_x = tf.transpose(x)
fn = lambda t: tf.reduce_prod(tf.boolean_mask(transpose_of_x, t), axis=0)
y = tf.stack([fn(i) for i in tf.unstack(map_x_on_y, axis=1)])

init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(x.eval())
    print(map_x_on_y)
    print(y.eval())
 
 生成正确的输出： 
 
[[  1.   2.   3.]
 [  4.   5.   6.]
 [  7.   8.   9.]
 [ 10.  11.  12.]]
[[ True False]
 [False False]
 [ True  True]]
[[   3.   24.   63.  120.]
 [   3.    6.    9.   12.]]
 
 作为张量流动的初学者，我将非常感谢您的帮助，对定义的操作进行梯度评估时会出现什么问题？ 
 
 最好的巴斯蒂安 

I have a problem, when trying to use tensorflow's boolean_mask function together with the gradient optimizer (tensorflow version 0.12.1 on Windows x64 with Anaconda 3.5).
 
import tensorflow as tf
import numpy as np

# Test data
x_dat = np.arange(1, 13).reshape(4, 3).astype(np.float32)
y_dat = np.arange(1, 9).reshape(4, 2).astype(np.float32) 
map_x_on_y = np.array([[True, False], [False, False], [ True, True]])

# Test data
x = tf.placeholder(tf.float32, [None, 3])
y_ = tf.placeholder(tf.float32, [None, 2])

# Model: Take the column product of the elements of x using the rows of               
# map_x_on_y as a filter. 
# The two columns of map_x_on_y give the two columns of y

transpose_of_x = tf.transpose(x)
fn = lambda t: tf.reduce_prod(tf.boolean_mask(transpose_of_x, t), axis=0)
y = tf.stack([fn(i) for i in tf.unstack(map_x_on_y, axis=1)])

# Train the model
sum_of_squared_errors = tf.reduce_mean(tf.square(y_-y)) 
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(sum_of_squared_errors)
init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)
    feed_dict ={x: x_dat, y_: y_dat} 
    for i in range(10):   
        sess.run([train_step], feed_dict)
 
I get the following error message:
 
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-108-cc039c0c3ed9> in <module>()
    21 # Train the model
    22 sum_of_squared_errors = tf.reduce_mean(tf.square(y_-y))
    ---> 23 train_step =                 tf.train.GradientDescentOptimizer(0.1).minimize(sum_of_squared_errors)
    24 init = tf.global_variables_initializer()
    25 

C:\Anaconda3\lib\site-packages\tensorflow\python\training\optimizer.py in minimize(self, loss, global_step, var_list, gate_gradients, aggregation_method, colocate_gradients_with_ops, name, grad_loss)
    274           "No gradients provided for any variable, check your graph for ops"
    275           " that do not support gradients, between variables %s and loss %s." %
    --> 276           ([str(v) for _, v in grads_and_vars], loss))
    277 
    278     return self.apply_gradients(grads_and_vars, global_step=global_step,

    ValueError: No gradients provided for any variable, check your graph for        ops that do not support gradients, between variables ['Tensor("Variable/read:0", shape=(3, 10), dtype=bool)', 'Tensor("Variable_1/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_2/read:0", shape=(3, 10), dtype=bool)', 'Tensor("Variable_3/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_4/read:0", shape=(3, 10), dtype=float64)', 'Tensor("Variable_5/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_6/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_7/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_8/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_9/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_10/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_11/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_12/read:0", shape=(3, 5), dtype=float64)', 'Tensor("Variable_13/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_14/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_15/read:0", shape=(5, 3), dtype=int32)', 'Tensor("Variable_16/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_17/read:0", shape=(5, 3), dtype=int32)', 'Tensor("Variable_18/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_19/read:0", shape=(5, 3), dtype=float32)', 'Tensor("Variable_20/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_21/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_22/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_23/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_24/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_25/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_26/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_27/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_28/read:0", shape=(3, 2), dtype=float32)', 'Tensor("Variable_29/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_30/read:0", shape=(3, 2), dtype=float32)', 'Tensor("Variable_31/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_32/read:0", shape=(3, 2), dtype=float32)', 'Tensor("Variable_33/read:0", shape=(3, 5), dtype=float32)', 'Tensor("Variable_34/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_35/read:0", shape=(5, 3), dtype=float32)', 'Tensor("Variable_36/read:0", shape=(3, 2), dtype=bool)', 'Tensor("Variable_37/read:0", shape=(5, 3), dtype=float32)', 'Tensor("Variable_38/read:0", shape=(3, 2), dtype=bool)'] and loss Tensor("Mean_1:0", shape=(), dtype=float32).
 
The operation seem to work fine, when using only variables:
 
import tensorflow as tf
import numpy as np

x = tf.Variable(np.arange(1, 13).reshape(4, 3).astype(np.float32))
map_x_on_y = np.array([[True, False], [False, False], [ True, True]])

transpose_of_x = tf.transpose(x)
fn = lambda t: tf.reduce_prod(tf.boolean_mask(transpose_of_x, t), axis=0)
y = tf.stack([fn(i) for i in tf.unstack(map_x_on_y, axis=1)])

init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(x.eval())
    print(map_x_on_y)
    print(y.eval())
 
Producing the correct output:
 
[[  1.   2.   3.]
 [  4.   5.   6.]
 [  7.   8.   9.]
 [ 10.  11.  12.]]
[[ True False]
 [False False]
 [ True  True]]
[[   3.   24.   63.  120.]
 [   3.    6.    9.   12.]]
 
Being a beginner in tensorflow, I would highly appreciate your help, what is going wrong with the gradient evaluation of the defined operation?
 
Best Bastian

原文：https://stackoverflow.com/questions/41743093