数值错误：维度必须相等，但是'MatMul_1'的输入形状为[?,784]和[500,500]，维度分别为784和500。（操作：MatMul）

Question

我是一名TensorFlow的新手，正在跟随sentdex的教程学习。然而我一直遇到以下错误 -

ValueError: Dimensions must be equal, but are 784 and 500 for 
'MatMul_1' (op: 'MatMul') with input shapes: [?,784], [500,500].

我认为引起问题的片段是这个-

l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), 
hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)

l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']), 
hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)

l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), 
hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)

output = tf.add(tf.matmul(l3, output_layer['weights']), 
output_layer['biases'])

return output

尽管我是个新手，也可能错了。我的整个代码就是-

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

n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500

n_classes = 10
batch_size = 100

x = tf.placeholder('float', [None, 784])
y = tf.placeholder('float')


def neural_network_model(data):
hidden_1_layer = {'weights': tf.Variable(tf.random_normal([784, 
n_nodes_hl1])),
                  'biases': 
tf.Variable(tf.random_normal([n_nodes_hl1]))}

hidden_2_layer = {'weights': 
tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                  'biases': 
tf.Variable(tf.random_normal([n_nodes_hl2]))}

hidden_3_layer = {'weights': 
tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
                  'biases': 
tf.Variable(tf.random_normal([n_nodes_hl3]))}

output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl3, 
n_classes])),
                'biases': tf.Variable(tf.random_normal([n_classes]))}

l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), 
hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)

l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']), 
hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)

l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), 
hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)

output = tf.add(tf.matmul(l3, output_layer['weights']), 
output_layer['biases'])

return output


def train_neural_network(x):
prediction = neural_network_model(x)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits
(logits=prediction, labels=y))
optimizer = tf.train.AdamOptimizer().minimize(cost)

hm_epochs = 10

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    for epoch in range(hm_epochs):
        epoch_loss = 0
        for _ in range(int(mnist.train.num_examples / batch_size)):
            epoch_x, epoch_y = mnist.train.next_batch(batch_size)
            _, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, 
y: epoch_y})
            epoch_loss += c
        print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:', 
epoch_loss)

    correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
    print('Accuracy:', accuracy.eval({x: mnist.test.images, y: 
mnist.test.labels}))


train_neural_network(x)

请帮忙。顺便提一下，我在 Mac 上运行 Python 3.6.1 和 Tensorflow 1.2 的虚拟环境中，并使用 Pycharm CE IDE。如果这些信息有用的话。

- Osiris.N

---

请修复您的缩进，由于现在的缩进问题，我无法运行您的代码来尝试复制该错误。 - Ofer Sadan

我会在 neural_network_model 的每一行之间添加 print(l1.get_shape().as_list())，以尝试找出问题所在。 - finbarr

Answer 1

问题在于你引用了 data 而不是 l1。应该改为：

l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']), 
                      hidden_2_layer['biases'])

您的代码应该这样编写：

l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), 
                      hidden_2_layer['biases'])

并且对于 l3 也是同样的情况。不要使用

l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), 
                      hidden_3_layer['biases'])

您应该具备

l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), 
                      hidden_3_layer['biases'])

以下代码在我的电脑上运行没有出现错误：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

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

n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500

n_classes = 10
batch_size = 100

x = tf.placeholder('float', [None, 784])
y = tf.placeholder('float')

def print_shape(obj):
    print(obj.get_shape().as_list())

def neural_network_model(data):
    hidden_1_layer = {'weights': tf.Variable(tf.random_normal([784,
                                                               n_nodes_hl1])),
                      'biases':
                      tf.Variable(tf.random_normal([n_nodes_hl1]))}

    hidden_2_layer = {'weights':
                      tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                      'biases':
                      tf.Variable(tf.random_normal([n_nodes_hl2]))}

    hidden_3_layer = {'weights':
                      tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
                      'biases':
                      tf.Variable(tf.random_normal([n_nodes_hl3]))}

    output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl3,
                                                             n_classes])),
                    'biases': tf.Variable(tf.random_normal([n_classes]))}
    print_shape(data)
    l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']),
                hidden_1_layer['biases'])
    print_shape(l1)
    l1 = tf.nn.relu(l1)
    print_shape(l1)
    l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']),
                hidden_2_layer['biases'])
    l2 = tf.nn.relu(l2)

    l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']),
                hidden_3_layer['biases'])
    l3 = tf.nn.relu(l3)

    output = tf.add(tf.matmul(l3, output_layer['weights']),
                    output_layer['biases'])

    return output


def train_neural_network(x):
    prediction = neural_network_model(x)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits
                          (logits=prediction, labels=y))
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 10

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())

        for epoch in range(hm_epochs):
            epoch_loss = 0
            for _ in range(int(mnist.train.num_examples / batch_size)):
                epoch_x, epoch_y = mnist.train.next_batch(batch_size)
                _, c = sess.run([optimizer, cost], feed_dict={x: epoch_x,
                                                              y: epoch_y})
                epoch_loss += c
            print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:',
                  epoch_loss)

        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy:', accuracy.eval({x: mnist.test.images, y:
                                          mnist.test.labels}))


train_neural_network(x)

- finbarr

---

没问题 :) 如果您喜欢我的回答，能否请您接受它呢？ - finbarr

抱歉，忘记了。 :) - Osiris.N

嗨！我正在处理同样的代码，但是在我的数据集上运行，有人可以指导我吗？ - FAHAD SIDDIQUI