我正在跟随Sentdex在YouTube上的示例,以下是我的代码
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 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(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.matmul(l3,output_layer['weights']) + output_layer['biases']
return output
def train_neural_network(x):
prediction = neural_network_model(x)
# OLD VERSION:
#cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
# NEW:
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:
# OLD:
#sess.run(tf.initialize_all_variables())
# NEW:
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)
它会产生这个错误:
ValueError: Shapes must be equal rank, but are 2 and 1
From merging shape 0 with other shapes. for 'SparseSoftmaxCrossEntropyWithLogits/packed' (op: 'Pack') with input shapes: [?,10], [10].
在这一行上:
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y) )
我认为导致错误的是y的大小,我尝试使用。
cost = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
prediction, tf.squeeze(y)))
我很确定这意味着成本函数引起了误差(如上所示)的预测和y不是相同的形状,但我不理解TensorFlow足够好,不知道如何修复它。我甚至不知道y在哪里被设置的,我从教程中获取了大部分代码并对其进行了调整以应用于不同的数据集。我该如何修复这个错误?另外,我尝试打印出预测值,它给了我两个输出,我猜这就是错误的来源。
prediction
(<tf.Tensor 'MatMul_39:0' shape=(?, 10) dtype=float32>,
<tf.Variable 'Variable_79:0' shape=(10,) dtype=float32_ref>)