如何使用Tensorflow在CNN中訓練圖像

Question

我是TensorFlow的初學者，我正嘗試構建到CNN模型。 以下是我參考的示例代碼： https://github.com/MorvanZhou/tutorials/blob/master/tensorflowTUT/tf18_CNN3/full_code.py

目前我正面臨一個問題。我不知道如何將訓練數據（圖像）插入到我的模型中。

的示例代碼使用：

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

雖然我需要用我自己的圖像作爲訓練數據。

從示例代碼：

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

我不是很懂這個，我怎麼能在我的代碼做來實現這個功能？謝謝。

下面是我的代碼：

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)) 

這是錯誤的屏幕後，我跑我的代碼。

Answer 1

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

這是主要的問題。在將圖像插入輸入隊列時，您沒有將標籤與它一起指定。

如果你看看Tensorflow教程例如，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) 

所以刪除getTrainLabels()功能，並與resize_image一起推標籤插入隊列。