Question

我是TensorFlow的初学者，我正在尝试构建CNN模型。这是我引用的示例代码： https://github.com/MorvanZhou/tutorials/blob/master/tensorflowTUT/tf18_CNN3/full_code.py

目前我遇到了一个问题。我不知道如何将训练数据（图像）插入到我的模型中。

示例代码正在使用：

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

虽然我需要使用自己的图像作为训练数据。

来自示例代码：

batch_xs, batch_ys = mnist.train.next_batch(100)

我真的不明白这一点，我怎样才能在我的代码中实现这个功能？感谢。

以下是我的代码：

from __future__ import print_function
import tensorflow as tf

def getTrainImages():
    filenames=[]
    for i in range(576,1151):
        if i<1000:
            filenames.append('data/Class1/Class1/Train/0'+str(i)+'.PNG')
        else:
            filenames.append('data/Class1/Class1/Train/'+str(i)+'.PNG')
    # step 2
    filename_queue = tf.train.string_input_producer(filenames)

    # step 3: read, decode and resize images
    reader = tf.WholeFileReader()
    filename, content = reader.read(filename_queue)
    image = tf.image.decode_jpeg(content, channels=1)
    image = tf.cast(image, tf.float32)
    resized_image = tf.image.resize_images(image, 512, 512)

    # step 4: Batching
    image_batch = tf.train.batch([resized_image], batch_size=100)
    return image_batch

def getTrainLabels():
    labels=[]
    file = open('data/Class1/Class1/Train/Label/Labels.txt', 'r')
    for line in file:
        if len(line)<=25:
            labels.append(0)
        else:
            labels.append(1)
    return labels

def getTestImages():
    filenames=[]
    for i in range(1,576):
        if i<10:
            filenames.append('data/Class1/Class1/Test/000'+str(i)+'.PNG')
        elif i<100:
            filenames.append('data/Class1/Class1/Test/00'+str(i)+'.PNG')
        elif i<1000:
            filenames.append('data/Class1/Class1/Test/0'+str(i)+'.PNG')
        else:
            filenames.append('data/Class1/Class1/Test/'+str(i)+'.PNG')
    # step 2
    filename_queue = tf.train.string_input_producer(filenames)

    # step 3: read, decode and resize images
    reader = tf.WholeFileReader()
    filename, content = reader.read(filename_queue)
    image = tf.image.decode_jpeg(content, channels=1)
    image = tf.cast(image, tf.float32)
    resized_image = tf.image.resize_images(image, 512, 512)

    # step 4: Batching
    image_batch = tf.train.batch([resized_image], batch_size=100)
    return image_batch

def getTestLabels():
    labels=[]
    file = open('data/Class1/Class1/Test/Label/Labels.txt', 'r')
    for line in file:
        if len(line)<=25:
            labels.append(0)
        else:
            labels.append(1)
    return labels

def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
    return result

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):
    # stride [1, x_movement, y_movement, 1]
    # Must have strides[0] = strides[3] = 1
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') #SAME or VALID

def max_pool_2x2(x):
    # stride [1, x_movement, y_movement, 1]
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 262144]) # 512x512
ys = tf.placeholder(tf.float32, [None, 2])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 512, 512, 1])
# print(x_image.shape)  # [n_samples, 512,512,1]

## conv1 layer ##
W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 512x512x32
h_pool1 = max_pool_2x2(h_conv1)                                         # output size 256x256x32

## conv2 layer ##
W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 256x256x64
h_pool2 = max_pool_2x2(h_conv2)                                         # output size 128x128x64

## func1 layer ##
W_fc1 = weight_variable([128*128*64, 256])
b_fc1 = bias_variable([256])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
h_pool2_flat = tf.reshape(h_pool2, [-1, 128*128*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

## func2 layer ##
W_fc2 = weight_variable([256, 2]) # only 2 class, defect or defect-free
b_fc2 = bias_variable([2])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)


# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))       # loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

sess = tf.Session()
# important step
sess.run(tf.initialize_all_variables())

batch_xs = getTrainImages()
batch_ys = getTrainLabels()
test_images = getTestImages()
test_labels = getTestLabels()
for i in range(1000):
    #batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
    if i % 50 == 0:
        print(compute_accuracy(
            test_images, test_labels))

运行我的代码后，这是错误屏幕。

Answer 1

    image_batch = tf.train.batch([resized_image], batch_size=100)

这是主要问题。将图像插入输入队列时，未指定标签。

如果您查看Tensorflow教程示例https://github.com/tensorflow/tensorflow/blob/r0.11/tensorflow/models/image/cifar10/cifar10_input.py#L126

images, label_batch = tf.train.batch(
    [image, label],
    batch_size=batch_size,
    num_threads=num_preprocess_threads,
    capacity=min_queue_examples + 3 * batch_size)

所以删除getTrainLabels()函数并将标签与resize_image一起推入队列。

如何使用Tensorflow在CNN中训练图像

1 个答案: