我是TensorFlow的新手,我正在尝试编写一个算法来对CIFAR-10数据集中的图像进行分类。我收到此错误:tf.nn.softmax_cross_entropy_with_logits()错误:logits和标签必须大小相同
InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[10000,10] labels_size=[1,10000]
[[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape, Reshape_1)]]
这里是我的代码:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import cPickle
n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500
n_classes = 10
batch_size = 100
image_size = 32*32*3 # because 3 channels
x = tf.placeholder('float', shape=(None, image_size))
y = tf.placeholder('float')
def neural_network_model(data):
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([image_size, 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(I am new to TensorFlow and tf.random_normal([n_nodes_hl3, n_classes])), 'biases':tf.Variable(tf.random_normal([n_classes]))}
# input_data * weights + biases
l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
# activation function
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)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction, y))//THIS IS LINE 48 WHERE THE ERROR OCCURS
#learning rate = 0.001
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for epoch in range(hm_epochs):
epoch_loss = 0
for i in range(5):
with open('data_batch_'+str(i+1),'rb') as f:
train_data = cPickle.load(f)
print train_data
print prediction.get_shape()
#print len(y)
_, c = sess.run([optimizer, cost], feed_dict={x:train_data['data'],y:train_data['labels']})
epoch_loss += c
print 'Epoch ' + str(epoch) + ' completed out of ' + str(hm_epochs) + ' loss: ' + str(epoch_loss)
correct = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
with open('test_batch','rb') as f:
test_data = cPickle.load(f)
accuracy = accuracy.eval({x:test_data['data'],y:test_data['labels']})
print 'Accuracy: ' + str(accuracy)
train_neural_network(x)
我敢肯定,这意味着在48行(如上图所示)prediction
和y
是不一样的形状,但我不明白TensorFlow足够知道如何解决它。我甚至不知道在哪里设置了y
,我从教程中获得了大部分代码,并将其用于应用于不同的数据集。我该如何解决这个错误?
我接着说:tf.squeeze()'和我仍然得到同样的错误 –
你怎么也SWI tch to'tf.nn.sparse_softmax_cross_entropy_with_logits()'? – mrry
没有看到,谢谢。现在我得到'TypeError:DataType float32 attr'Tlabels'不在允许值列表中:int32,int64'我认为这与你所谈论的有关。我可以将'y = tf.placeholder('float')'改成'y = tf.placeholder('int')'吗? –