ValueError：尺寸必须相等，但输入形状为 [?,784]、[500,500] 的“MatMul_1”（操作：“MatMul”）的尺寸为 784 和 500

Question

我是 tensorflow 的新手，我正在学习 sentdex 的教程。我不断收到错误 -

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

我认为导致问题的 sn-p 是 -

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

虽然我是个菜鸟，可能是错的。我的整个代码是 -

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。顺便说一句，我在带有 Python 3.6.1 和 Tensorflow 1.2 的虚拟环境中在 Mac 上运行。我正在使用 IDE Pycharm CE。如果这些信息中的任何一个有用。

Answer 1

问题是您引用的是data 而不是l1。而不是

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

你的代码应该是这样的

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

l3 也是如此。而不是

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

你应该有

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

以下代码对我来说没有错误：

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)