tensorflow--sparse_softmax_cross_entropy_with_logits使用问题

[lyfuci]

求大神帮我解释一下这个函数的意义，以及在代码中应该如何具体使用。

# -*- coding: utf-8 -*-
"""
Created on Wed Sep 13 11:12:28 2017
实战goolge深度学习框架 5.2.1
@author: Sean
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# MNIST数据集相关的常数
INPUT_NODE=784
OUTPUT_NODE=10

LAYER1_NODE =500
BATCH_SIZE=100

LEARNING_RATE_BASE=0.8
LEARNING_RATE_DECAY=0.99

REGULARIZATION_RATE=0.0001
TRAINING_STEPS=30000
MOVING_AVERAGE_DECAY=0.99

def inference(input_tensor,avg_class,weights1,biases1,weights2,biases2):
    if avg_class==None:
        layer1=tf.nn.relu(tf.matmul(input_tensor,weights1)+biases1)
        
        return tf.matmul(layer1,weights2)+biases2
    else:
        layer1=tf.nn.relu(tf.matmul(input_tensor,avg_class.average(weights1))+avg_class.average(biases1))
        return tf.matmul(layer1,avg_class.average(weights2)+avg_class.average(biases2))
    
def train(mnist):
    x=tf.placeholder(tf.float32,[None,INPUT_NODE],name="x-input")
    y_=tf.placeholder(tf.float32,[None,OUTPUT_NODE],name="y-input")
    
    weights1=tf.Variable(tf.truncated_normal([INPUT_NODE,LAYER1_NODE],stddev=0.1))
    biases1=tf.Variable(tf.constant(0.1,shape=[LAYER1_NODE]))
    weights2=tf.Variable(tf.truncated_normal([LAYER1_NODE,OUTPUT_NODE],stddev=0.1))
    biases2=tf.Variable(tf.constant(0.1,shape=[OUTPUT_NODE]))
    
    #method 1
    y=inference(x,None,weights1,biases1,weights2,biases2)
    
    
    #method 2
    global_step=tf.Variable(0,trainable=False)
    
    variable_averages=tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)
    
    variable_averages_op=variable_averages.apply(tf.trainable_variables())
    
    average_y=inference(x,variable_averages,weights1,biases1,weights2,biases2)
    
    #cross_entropy =tf.nn.sparse_softmax_cross_entropy_with_logits(labels = y_, logits = y)
    cross_entropy =tf.nn.sparse_softmax_cross_entropy_with_logits(y, tf.argmax(y_, 1))
    cross_entropy_mean=tf.reduce_mean(cross_entropy)
    
    regularizer=tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    
    regularization=regularizer(weights1)+regularizer(weights2)
    
    loss=cross_entropy_mean+regularization
    
    learning_rate=tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)
    
    train_step=tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)
    
    
    with tf.control_dependencies([train_step,variable_averages_op]):
        train_op=tf.no_op(name="train")
        
    correct_prediction=tf.equal(tf.argmax(average_y,1),tf.arg_max(y,1))
    
    accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        
        validate_feed={x:mnist.validation.image,y_:mnist.validation.labels}
        
        test_feed={x:mnist.test.images,y_:mnist.test.labels}
        
        for i in range(TRAINING_STEPS):
            if i%1000==0:
                validate_acc=sess.run(accuracy,feed_dict={validate_feed})
                print("After %d training step(s),validation accuracy using average model is %g"%validate_acc)
            xs,ys=mnist.train.next_batch(BATCH_SIZE)
            sess.run(train_op,feed_dict={x:xs,y:ys})
        
        test_acc=sess.run(accuracy,feed_dict=test_feed)
        print("Agter %d training steps,test accuracy using average model is %g"%(TRAINING_STEPS,test_acc))
        
    
def main(argv=None):
    mnist=input_data.read_data_sets("/tmp/data",one_hot=True)
    train(mnist)
    
if __name__=='__main__':
    tf.app.run()

上面代码中55-56行报错，报错如下：


File "C:/Users/Sean/.spyder-py3/mnist_test.py", line 56, in train
cross_entropy =tf.nn.sparse_softmax_cross_entropy_with_logits(y, tf.argmax(y_, 1))

File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 1664, in sparse_softmax_cross_entropy_with_logits
labels, logits)

File "C:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 1512, in _ensure_xent_args
"named arguments (labels=..., logits=..., ...)" % name)

ValueError: Only call `sparse_softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...)

感觉看了一下TF1.3版本的文档，结果这个函数确实需要一个labels和logits参数，但是并不太明白该函数文档的意义，具体文档如下：
Definition : sparse_softmax_cross_entropy_with_logits(_sentinel=None, # pylint: disable=invalid-name labels=None, logits=None, name=None)

Type : Function in tensorflow.python.ops.nn_ops module

Args:
_sentinel: Used to prevent positional parameters. Internal, do not use. labels: Tensor of shape [d_0, d_1, …, d_{r-1}] (where r is rank of

labels and result) and dtype int32 or int64. Each entry in labels must be an index in [0, num_classes). Other values will raise an exception when this op is run on CPU, and return NaN for corresponding loss and gradient rows on GPU.
logits: Unscaled log probabilities of shape
[d_0, d_1, …, d_{r-1}, num_classes] and dtype float32 or float64.
name: A name for the operation (optional).


所以，求大神帮我解释一下这个函数的意义，以及在代码中应该如何具体使用，我知道可能有点麻烦，但是确实绝望了。。。

[Image-MJ]

cross_entropy =tf.nn.sparse_softmax_cross_entropy_with_logits(y_, tf.argmax(y_, 1)) 改为 cross_entropy=tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_,1),logits=y)即可

[z2539329562]

这是源码里有问题，你可以用pycharm跳过去看一下，一楼的方案是对的