我正在使用张量流创建卷积神经网络类，并遇到一个错误，在优化过程中，一个张量应具有40000个元素，而原本应该只有10000个。问题出现在行中：
correct_prediction = tf.equal(tf.argmax(self.y, 1), tf.argmax(output, 1))
给出错误：
InvalidArgumentError (see above for traceback): Incompatible shapes: [10000] vs. [40000]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ArgMax, ArgMax_1)]]
所以基本上说我的网络输出比我提供的测试标签大4倍。我的问题是，随着输出张量的变化，如何查看它的大小？似乎所有事情都通过单行代码session.run（'model-name'）在幕后发生，这使我无法对其进行调试。我如何查看内部情况并弄清楚发生了什么？
这是完整的代码：
class ConvNet:
def __init__(self, epochs=1, learning_rate=0.01, batch_size=50):
self.learning_rate = learning_rate
self.epochs = epochs
self.batch_size = batch_size
self.x = tf.placeholder(tf.float32, [None, 784])
self.x_shaped = tf.reshape(self.x, [-1, 28, 28, 1])
self.y = tf.placeholder(tf.float32, [None, 10])
self.accuracy = None
def predict(self, x_test, y_test):
with tf.Session() as sess:
new_saver = tf.train.import_meta_graph('convnet-model.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('./'))
test_acc = sess.run(self.accuracy, feed_dict={self.x: x_test, self.y: y_test})
print('test accuracy: {:.3f}'.format(test_acc))
def train(self, x_train, y_train):
output, raw_output = self.create_structure()
self.optimize(raw_output, output, x_train, y_train)
def create_structure(self):
output = self.conv_layer(self.x_shaped, 1, 32, [5, 5], 'conv1')
output = self.relu_layer(output)
output = self.conv_layer(output, 32, 64, [5, 5], 'conv2')
output = self.relu_layer(output)
output = self.max_pool_layer(output, [2, 2])
raw_output, output = self.full_connect_layers(output)
return output, raw_output
def optimize(self, raw_output, output, x_train, y_train):
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=raw_output, labels=output))
optimiser = tf.train.AdamOptimizer(learning_rate=self.learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(self.y, 1), tf.argmax(output, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init_op)
total_batch = int(len(y_train) / self.batch_size)
for epoch in range(self.epochs):
for i in range(total_batch):
batch_x, batch_y = self.get_batch(x_train, y_train)
_, c = sess.run([optimiser, cross_entropy], feed_dict={self.x: batch_x, self.y: batch_y})
saver = tf.train.Saver()
saver.save(sess, './convnet-model')
def conv_layer(self, input_data, num_input_channels, num_filters, filter_shape, name):
# setup the filter shape for tf.nn.conv2d
conv_filter_shape = [filter_shape[0], filter_shape[1], num_input_channels, num_filters]
# init weights and bias for the filter
weights = tf.Variable(tf.truncated_normal(conv_filter_shape, stddev=0.03), name=name+'_w')
bias = tf.Variable(tf.truncated_normal([num_filters]), name=name+'_b')
# set up the convolutional layer operation
out_layer = tf.nn.conv2d(input_data, weights, [1, 1, 1, 1], padding='SAME')
# add the bias
out_layer += bias
return out_layer
def relu_layer(self, out_layer):
return tf.nn.relu(out_layer)
def max_pool_layer(self, out_layer, pool_shape):
ksize = [1, pool_shape[0], pool_shape[1], 1]
strides = [1, 2, 2, 1]
out_layer = tf.nn.max_pool(out_layer, ksize=ksize, strides=strides, padding='SAME')
return out_layer
def full_connect_layers(self, output):
flattened = tf.reshape(output, [-1, 7 * 7 * 64])
w1 = tf.Variable(tf.truncated_normal([7*7*64, 1000], stddev=0.03), name='w1')
b1 = tf.Variable(tf.truncated_normal([1000], stddev=0.01), name='b1')
dense_layer1 = tf.matmul(flattened, w1) + b1
dense_layer1 = tf.nn.relu(dense_layer1)
w2 = tf.Variable(tf.truncated_normal([1000, 10], stddev=0.03), name='w2')
b2 = tf.Variable(tf.truncated_normal([10], stddev=0.01), name='b2')
dense_layer2 = tf.matmul(dense_layer1, w2) + b2
y = tf.nn.softmax(dense_layer2)
return dense_layer2, y
def get_batch(self, features, labels):
index_list = np.arange(0, len(labels))
np.random.shuffle(index_list)
new_features = np.asarray([features[i] for i in index_list])
new_labels = np.asarray([labels[i] for i in index_list])
return new_features[0:self.batch_size], new_labels[0:self.batch_size]
主文件：
from convnet import ConvNet
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
convnet = ConvNet()
convnet.train(mnist.test.images, mnist.test.labels)
convnet.predict(mnist.test.images, mnist.test.labels)