image - Tensorflow，train_step提要不正确

我正在从convnetjs切换到tensorflow并试图获得阅读图像和使用tensorflow训练cnn的基础知识。

我在两个文件夹中有一堆图像160 * 120 * 1:train/go和train/no，所以我使用两个类。

我以某种方式可以理解tf.train.slice_input_producer和sess.run(train_step之间的连接方式。

我的代码:

import tensorflow as tf

def read_my_list( minId, maxId ):
    """ create list with train/no and train/go from 1 to maxid
        max maxId = 50000
    """

    filenames = []
    labels = []
    for num in range( minId, maxId ):

        filenames.append( "/media/boss/tensor/train/go/" + str( num ) + ".jpg" )
        labels.append( int( 1 ) )

        filenames.append( "/media/boss/tensor/train/no/" + no_go_name( num ) + ".jpg" )
        labels.append( int( 0 ) )

        # return list with all filenames
    return filenames, labels

def no_go_name( id ):

    # create string where id = 5 becomes 00005

    ret = str( id )
    while ( len( ret ) < 5 ):
      ret = "0" + ret;

    return ret;


def read_images_from_disk(input_queue):
    """Consumes a single filename and label as a ' '-delimited string.
    Args:
      filename_and_label_tensor: A scalar string tensor.
    Returns:
      Two tensors: the decoded image, and the string label.
    """
    label = input_queue[1]
    print( "read file "  )
    file_contents = tf.read_file(input_queue[0])
    example = tf.image.decode_jpeg(file_contents, channels=1)

    # do i need to set shape??????????
    example.set_shape([160, 120, 1])
    print( "file read " )
    return  example, label



# some stuff to create a cnn etc
x = tf.placeholder(tf.float32, [None, 19200])

W = tf.Variable(tf.zeros([19200, 2]))
b = tf.Variable(tf.zeros([2]))

y = tf.nn.softmax(tf.matmul(x, W) + b)

y_ = tf.placeholder(tf.float32, [None, 2])

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

init = tf.initialize_all_variables()

with tf.Session() as sess:
    sess.run(init)

    # get filelist and labels
    image_list, label_list = read_my_list( 1, 10 )

    # conver to tensors for input_queue
    images = tf.convert_to_tensor(image_list, dtype=tf.string)
    labels = tf.convert_to_tensor(label_list, dtype=tf.int32)

    # Makes an input queue
    input_queue = tf.train.slice_input_producer([images, labels],
                                        num_epochs=10,
                                        shuffle=True)

    image, label = read_images_from_disk(input_queue)

    for i in range(100):
        print( i )

        image_batch, label_batch = tf.train.batch([image, label],
                                          batch_size=2)


        #gives error see below
        sess.run(train_step, feed_dict={x: image_batch, y_: label_batch})


    # test accuracy, unsure if something is wrong here
    correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    batch_xs, batch_ys = tf.train.batch([image, label],
                                      batch_size=10)

    print(sess.run(accuracy, feed_dict={x: batch_xs, y_: batch_ys}))

下面的行给出了一个错误:

sess.run(train_step, feed_dict={x: image_batch, y_: label_batch})

这是错误:

Traceback (most recent call last):

File "detectGoNo.py", line 95, in <module>
sess.run(train_step, feed_dict={x: image_batch, y_: label_batch})

File "/home/boss/anaconda2/envs/tensor2/lib/python2.7/site-
packages/tensorflow/python/client/session.py", line 340, in run

run_metadata_ptr)

File "/home/boss/anaconda2/envs/tensor2/lib/python2.7/site-
packages/tensorflow/python/client/session.py", line 545, in _run

raise TypeError('The value of a feed cannot be a tf.Tensor object. '

TypeError: The value of a feed cannot be a tf.Tensor object. Acceptable
feed values include Python scalars, strings, lists, or numpy ndarrays.

更新02-06-2016

我从nessuno，培训和验证中获得了与该解决方案一起使用的所有功能(下面的代码)
Mrry指出，不幸的是，一条管道比较典型，这是行不通的(下面的代码)
没有给出任何错误，但计算的成本保持不变，并且验证表明我的网络没有改善。

我最好的猜测是，我将标签馈给培训师的方式或我使用one_hot函数的方式出了点问题。

验证部分似乎正在工作，当我感觉始终带有0标签精度的图像变为100％，1标签精度为0％且50/50时为50％。当然也可以相反，但是由于培训期间成本没有改变，我认为培训期间出了点问题

我知道，我现在使用的模型很简单，但是对于调试它来说已经足够好了，工作版本可以在1500张图像中达到80％的精度。

label = tf.cast( label, tf.int64 )

label = tf.one_hot( label, 2, 0, 1 )
label = tf.cast( label, tf.float32 )

我的代码:(有效)

import tensorflow as tf
import numpy      as np
import math

IMAGE_WIDTH  = 160
IMAGE_HEIGHT = 120
IMAGE_DEPTH  = 1
IMAGE_PIXELS = IMAGE_WIDTH * IMAGE_HEIGHT
NUM_CLASSES  = 2

STEPS         = 50000
STEP_PRINT    = 100
STEP_VALIDATE = 100
LEARN_RATE    = 0.0014
DECAY_RATE    = 0.4
BATCH_SIZE    = 5

def read_my_list( minId, maxId, folder ):
    """ create list with train/no and train/go from 1 to maxid
        max maxId = 50000
    """

    filenames = []
    labels    = []
    #labels = np.zeros( ( ( maxId - minId ) * 2, 2 ) )
    for num in range( minId, maxId ):

        filenames.append( "/media/boss/2C260F93260F5CE8/tensor/" + folder + "/go/" + str( num ) + ".jpg" )
        #labels[ ( num - minId ) * 2 ][ 1 ] = 1
        labels.append( int( 1 ) )

        filenames.append( "/media/boss/2C260F93260F5CE8/tensor/" + folder + "/no/" + no_go_name( num ) + ".jpg" )
        #labels[ ( ( num - minId ) * 2 ) + 1 ][ 0 ] = 1
        labels.append( int( 0 ) )

        # return list with all filenames
    print( "label: " + str( len( labels ) ) )
    print( "image: " + str( len( filenames ) ) )
    return filenames, labels

def no_go_name( id ):

    # create string where id = 5 becomes 00005

    ret = str( id )
    while ( len( ret ) < 5 ):
      ret = "0" + ret;

    return ret;

# Create model
def conv_net(x):

    img_width  = IMAGE_WIDTH
    img_height = IMAGE_HEIGHT
    img_depth  = IMAGE_DEPTH

    weights    = tf.Variable( tf.random_normal( [ img_width * img_height * img_depth, NUM_CLASSES ] ) )
    biases     = tf.Variable( tf.random_normal( [ NUM_CLASSES ] ) )

    # softmax layer
    out        = tf.add( tf.matmul( x, weights ), biases )
    return out

def read_images_from_disk(input_queue):
    """Consumes a single filename and label as a ' '-delimited string.
    Args:
      filename_and_label_tensor: A scalar string tensor.
    Returns:
      Two tensors: the decoded image, and the string label.
    """
    label = input_queue[1]
    print( "read file "  )
    file_contents = tf.read_file(input_queue[0])
    example = tf.image.decode_jpeg( file_contents, channels = 1 )

    example = tf.reshape( example, [ IMAGE_PIXELS ] )
    example.set_shape( [ IMAGE_PIXELS ] )

    example = tf.cast( example, tf.float32 )
    example = tf.cast( example, tf.float32 ) * ( 1. / 255 ) - 0.5

    label = tf.cast( label, tf.int64 )

    label = tf.one_hot( label, 2, 0, 1 )
    label = tf.cast( label, tf.float32 )

    print( "file read " )
    return  example, label

with tf.Session() as sess:

    ########################################
    # get filelist and labels for training
    image_list, label_list = read_my_list( 501, 50000, "train" )

    # create queue for training
    input_queue = tf.train.slice_input_producer( [ image_list, label_list ],
                                                num_epochs = 100,
                                                shuffle = True )

    # read files for training
    image, label = read_images_from_disk( input_queue )

    # `image_batch` and `label_batch` represent the "next" batch
    # read from the input queue.
    image_batch, label_batch = tf.train.batch( [ image, label ], batch_size = BATCH_SIZE )

    # input output placeholders

    x = tf.placeholder(tf.float32, [None, IMAGE_PIXELS])
    y_ = tf.placeholder(tf.float32, [None, NUM_CLASSES])

    # create the network
    y = conv_net( x )

    # loss
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits( y, y_) )

    learning_rate = tf.placeholder(tf.float32, shape=[])

    # train step
    train_step   = tf.train.AdamOptimizer( 1e-3 ).minimize( cost )


    ########################################
    # get filelist and labels for validation
    image_list_test, label_list_test = read_my_list( 1, 500, "validation" )

    # create queue for validation
    input_queue_test = tf.train.slice_input_producer( [ image_list_test, label_list_test ],
                                                shuffle=True )

    # read files for validation
    image_test, label_test = read_images_from_disk( input_queue_test )

    # `image_batch_test` and `label_batch_test` represent the "next" batch
    # read from the input queue test.
    image_batch_test, label_batch_test = tf.train.batch( [ image_test, label_test ], batch_size=200 )

    correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    init = tf.initialize_all_variables()
    sess.run(init)

    # N.B. You must run this function before `sess.run(train_step)` to
    # start the input pipeline.
    #tf.train.start_queue_runners(sess)
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)

    for i in range(STEPS):
        # No need to feed, because `x` and `y_` are already bound to
        # the next input batch.
        if i % STEP_PRINT == 0:
            LEARN_RATE = LEARN_RATE * DECAY_RATE
            print( str( i ) + " " + str( LEARN_RATE ) )

        if i % STEP_VALIDATE == 0:

            imgs, lbls = sess.run([image_batch_test, label_batch_test])

            print(sess.run(accuracy, feed_dict={
                    x: imgs,
                    y_: lbls}))

        imgs, lbls = sess.run([image_batch, label_batch])

        sess.run(train_step, feed_dict={
         x: imgs,
         y_: lbls})
#         ,learning_rate:LEARN_RATE})

    imgs, lbls = sess.run([image_batch_test, label_batch_test])

    print(sess.run(accuracy, feed_dict={
         x: imgs,
         y_: lbls}))

    coord.request_stop()
    coord.join(threads)

我的代码:(不起作用)

with tf.Session() as sess:

    ########################################
    # get filelist and labels for training
    image_list, label_list = read_my_list( 501, 50000, "train" )

    # create queue for training
    input_queue = tf.train.slice_input_producer( [ image_list, label_list ],
                                                num_epochs = 100,
                                                shuffle = True )

    # read files for training
    image, label = read_images_from_disk( input_queue )

    # `image_batch` and `label_batch` represent the "next" batch
    # read from the input queue.
    image_batch, label_batch = tf.train.batch( [ image, label ], batch_size = BATCH_SIZE )

    x = image_batch
    y_ = label_batch

    # create the network
    y = conv_net( x )

    # loss
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits( y, y_) )

    # train step
    train_step   = tf.train.AdamOptimizer( 1e-3 ).minimize( cost )


    ########################################
    # get filelist and labels for validation
    image_list_test, label_list_test = read_my_list( 1, 500, "validation" )

    # create queue for validation
    input_queue_test = tf.train.slice_input_producer( [ image_list_test, label_list_test ],
                                                shuffle=True )

    # read files for validation
    image_test, label_test = read_images_from_disk( input_queue_test )

    # `image_batch_test` and `label_batch_test` represent the "next" batch
    # read from the input queue test.
    image_batch_test, label_batch_test = tf.train.batch( [ image_test, label_test ], batch_size=200 )

    xval = image_batch_test
    yval_ = label_batch_test

    # network for validation
    yval = conv_net( xval )

    # validate network
    correct_prediction = tf.equal( tf.argmax( yval, 1 ), tf.argmax( yval_, 1 ) )

    # calculate accuracy
    accuracy = tf.reduce_mean( tf.cast( correct_prediction, tf.float32 ) )

    # init all variables
    init = tf.initialize_all_variables()
    sess.run( init )

    # N.B. You must run this function before `sess.run(train_step)` to
    # start the input pipeline.
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners( coord = coord )

    for i in range(STEPS):
        # No need to feed, because `x` and `y_` are already bound to
        # the next input batch.
        if i % STEP_PRINT == 0:
            print( i )

        # validate accuracy
        if i % STEP_VALIDATE == 0:
            print( sess.run( accuracy ) )

        # train one step
        sess.run( train_step )

    # validate accuracy
    print( sess.run( accuracy ) )

    coord.request_stop()
    coord.join( threads )

更新2016年10月6日
我花了一段时间才意识到，训练流水线和验证流水线并不具有相同的权重和偏见。
现在，我训练，保存模型并将模型加载到单独的脚本中，就像一个吊饰一样工作。

最佳答案

作为nessuno points out， tf.train.batch() 的结果(image_batch和label_batch)是tf.Tensor对象，因此您不能将它们用作值以馈入子图。

使用tf.train.batch()的典型方法是使用它来定义管道的输入(而不是将tf.placeholder()用于x和y_)，以便在TensorFlow图中处理批处理和预取。这是对程序第一部分的大致重组，该部分根据需要执行批处理:

with tf.Session() as sess:

    # get filelist and labels
    image_list, label_list = read_my_list( 1, 10 )

    input_queue = tf.train.slice_input_producer([image_list, label_list],
                                                num_epochs=10,
                                                shuffle=True)

    image, label = read_images_from_disk(input_queue)

    # `image_batch` and `label_batch` represent the "next" batch
    # read from the input queue.
    image_batch, label_batch = tf.train.batch([image, label], batch_size=2)

    x = image_batch
    y_ = label_batch

    # Define your model in terms of `x` and `y_` here....
    train_step = ...

    # N.B. You must run this function after creating your graph.
    init = tf.initialize_all_variables()
    sess.run(init)

    # N.B. You must run this function before `sess.run(train_step)` to
    # start the input pipeline.
    tf.train.start_queue_runners(sess)

    for i in range(100):
        # No need to feed, because `x` and `y_` are already bound to
        # the next input batch.
        sess.run(train_step)

关于image - Tensorflow，train_step提要不正确，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/37454932/