我正在尝试为MNIST数据集训练一个带张量流的简单网络。 目前虽然它不起作用。 它基本上是TensorFlow网站上给出的示例的修改版本。我只是更改了几行并删除了一层以查看发生了什么。 这是我的代码:
#!/usr/bin/python
import input_data
import tensorflow as tf
#MNIST dataset
def weight_variable(shape):
initial=tf.truncated_normal(shape,stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial=tf.constant(0.1,shape=shape)
return tf.Variable(initial)
def conv2d(x,W):
return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
mnist=input_data.read_data_sets('MNIST_data',one_hot=True)
x=tf.placeholder("float",shape=[None,784])
y=tf.placeholder("float",shape=[None,10])
x_image=tf.reshape(x,[-1,28,28,1])
#Layer 1: convolutional+max pooling
W_conv2=weight_variable([5,5,1,64])
b_conv2=bias_variable([64])
h_conv2=tf.nn.relu(conv2d(x_image,W_conv2)+b_conv2)
h_pool2=max_pool_2x2(h_conv2)
#Layer 2: ReLU+Dropout
W_fc1=weight_variable([7*7*64,1024])
b_fc1=bias_variable([1024])
h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])
h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
keep_prob=tf.placeholder("float")
h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob)
#Layer 3: softmax
W_fc4=weight_variable([1024,10])
b_fc4=bias_variable([10])
y_hat=tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc4)+b_fc4)
cross_entropy=-tf.reduce_sum(y*tf.log(y_hat))
train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
sess=tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
correct_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_hat,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,"float"))
for n in range(20000):
batch=mnist.train.next_batch(50)
if n % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch[0],y:batch[1],keep_prob:1.0})
print "step %d,training accuracy %g" % (n,train_accuracy)
sess.run(train_step,feed_dict={x:batch[0],y:batch[1],keep_prob:0.5})
print "test accuracy %g" % accuracy.eval(feed_dict={x:mnist.test.images, y:mnist.test.labels,keep_prob:1.0})
当我尝试执行它时崩溃给我一个ArgumentError:
W tensorflow/core/common_runtime/executor.cc:1027] 0x7fceb58a4200 Compute status: Invalid argument: Incompatible shapes: [50] vs. [200]
答案 0 :(得分:2)
你需要你的步幅大小才能将你的输出减少到正确的形状 - 这应该解决它(注意与你的相比大步):
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 2, 2, 1], padding='SAME')
要解决此类问题,请尝试为所有变量打印.get_shape()
。 Tensor和Variable都具有此功能 - 它可以让您更好地了解正在发生的事情,并将极大地帮助您进行故障排除。
以下是一些有用的代码 - 在声明h_pool2
之后将其打印出来,它会打印出每个变量的名称和形状:
from tensorflow.python.ops.variables import Variable
for k, v in locals().items():
if type(v) is Variable or type(v) is tf.Tensor:
print("{0}: {1}".format(k, v))