ValueError:没有为任何变量提供渐变

Question

我正面临着tensorFlow的麻烦.执行以下代码

import tensorflow as tf
import input_data

learning_rate = 0.01
training_epochs = 25
batch_size = 100
display_step = 1

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

# tensorflow graph input
X = tf.placeholder('float', [None, 784]) # mnist data image of shape 28 * 28 = 784
Y = tf.placeholder('float', [None, 10]) # 0-9 digits recognition = > 10 classes

# set model weights
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# Our hypothesis
activation = tf.add(tf.matmul(X, W),b)  # Softmax

# Cost function: cross entropy
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=activation, logits=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)  # Gradient Descen

我收到以下错误:

ValueError:没有为任何变量提供渐变,检查图表中不支持渐变的ops,变量之间['Tensor("Variable/read:0",shape =(784,10),dtype = float32)','Tensor ("Variable_1/read:0",shape =(10,),dtype = float32)']和丢失Tensor("Mean:0",shape =(),dtype = float32).

Answer 1

此问题是由以下行引起的: tf.nn.softmax_cross_entropy_with_logits(labels=activation, logits=Y)

根据你应该有的文件

标签:每行标签[i]必须是有效的概率分布.

logits:未缩放的日志概率.

因此logits假设是你的假设,因此等于activation并且有效的概率分布是Y.所以只需改变它tf.nn.softmax_cross_entropy_with_logits(labels=Y, logits=activation)

Answer 2

我最终来到这里是因为我已将输入 X 数据传递给我的模型，但不是我预期的输出。我有：

model.fit(X, epochs=30)      # whoops!

我应该有：

model.fit(X, y, epochs=30)   # fixed!