我正在尝试使用shuffle_batch()函数将标签与张量流中的图像进行匹配，但是当我使用shuffle_batch（）函数开始训练循环时，有一个超出范围的RandomShuffleQueue 错误。
使用shuffle_batch函数时如何避免队列超出范围错误？
以下代码适用于前90步左右，准确度越来越高，直到它调用错误。
# Global Parameters
# Image Size
training_size = 1387
img_height = 64
img_width = 64
# File stream
batch_size = 128
# Training parameter
learning_rate = 0.001
training_iters = 100
keep_prob = 0.5 #dropout keep prob
display_step = 10
AdamOptimizer = 1
GradientDescentOptimizer = 0
# Filepath
csv_filepath = r'C:/Users/Jeffy/OneDrive/Course\NMDA\retinaProject\label.csv'
image_filepath = 'Image_P/'
import tensorflow as tf
# =============================================================================
# Read input data
# load csv content
csv_path = tf.train.string_input_producer(['label_3D.csv'])
textReader = tf.TextLineReader()
_, csv_content = textReader.read(csv_path)
im_name, col_2, col_3, col_4 = tf.decode_csv(csv_content, record_defaults=[[""], [1], [1], [1]])
label = tf.pack([col_2, col_3, col_4])
label_float32 = tf.cast(label, tf.float32)
# load images
im_content = tf.read_file(image_filepath + im_name+'.jpeg')
image = tf.image.decode_jpeg(im_content, channels=3)
image_float32 = tf.cast(image, tf.float32)/255
# Generate Batch
batch_shape = ((img_height, img_width, 3),(3))
images_batch, labels_batch = tf.train.shuffle_batch([image_float32, label_float32],
batch_size = batch_size,
capacity = batch_size * 50,
min_after_dequeue = batch_size * 10,
shapes = batch_shape)
# =============================================================================
# Construct Network
# define functions
def weight_varible(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')
# paras
W_conv1 = weight_varible([5, 5, 3, 32])
b_conv1 = bias_variable([32])
# conv layer-1
h_conv1 = tf.nn.relu(conv2d(images_batch, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# conv layer-2
W_conv2 = weight_varible([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
# full connection
W_fc1 = weight_varible([16 * 16 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 16 * 16 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# dropout
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# output layer: softmax
W_fc2 = weight_varible([1024, 3])
b_fc2 = bias_variable([3])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# model training
cross_entropy = -tf.reduce_sum(labels_batch * tf.log(y_conv))
if GradientDescentOptimizer:
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy)
else:
if AdamOptimizer:
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.arg_max(y_conv, 1), tf.arg_max(labels_batch, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# Start file queue
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
sess.run([images_batch, labels_batch])
coord.request_stop()
coord.join(threads)
for i in range(training_iters):
# display the result on console
if i % display_step == 0:
train_accuacy = accuracy.eval()
print("step %d, training accuracy %g"%(i, train_accuacy))
# run the model
train_step.run()
print("test accuracy %g"%(accuracy.eval()))
更新的代码在步骤90左右调用错误：
step 0, training accuracy 0.5625
step 10, training accuracy 0.6875
step 20, training accuracy 0.703125
step 30, training accuracy 0.625
step 40, training accuracy 0.65625
step 50, training accuracy 0.6875
step 60, training accuracy 0.6875
step 70, training accuracy 0.734375
step 80, training accuracy 0.632812
step 90, training accuracy 0.695312
然后
OutOfRangeError: RandomShuffleQueue '_24_shuffle_batch_3/random_shuffle_queue' is closed and has insufficient elements (requested 128, current size 1)
[[Node: shuffle_batch_3 = QueueDequeueMany[_class=["loc:@shuffle_batch_3/random_shuffle_queue"], component_types=[DT_FLOAT, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](shuffle_batch_3/random_shuffle_queue, shuffle_batch_3/n)]]
Caused by op 'shuffle_batch_3', defined at:
File "C:\Users\Jeffy\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 223, in <module>
main()
......
当我使用tf.batch（）将标签与图像匹配时，为什么图像的标签会粘在第一个样本上？ 我的老问题在Standy和我的朋友Dong的帮助下得到了解决。他们很多！
1.我的问题
在位置1或位置2上放置'shuffle_batch（）'函数的位置？ （您可以使用下面代码的tf.session（）部分找到它）
如何修复代码以使批处理成功地合并图像和标签，而不是粘在第一个例子上？
2.csv文件
图像名称和相关标签以下列格式存储在label.csv中（带标题）：
11219_right,0,1,0
15502_left,0,0,0
14481_right,0,1,0
11032_right,0,0,1
19322_right,0,0,0
......
3.Origin code
代码的目的是使用RNN作为图像分类器。
CNN结构基于张量流示例文件。
您可以专注于阅读数据部分和图表部分。
# Global Parameters
# Image Size
training_size = 1387
img_height = 64
img_width = 64
# File stream
batch_size = 128
# Training parameter
learning_rate = 0.001
training_iters = 100
keep_prob = 0.5 #dropout keep prob
display_step = 10
AdamOptimizer = 1
GradientDescentOptimizer = 0
# Filepath
csv_filepath = r'C:/Users/Jeffy/OneDrive/Course\NMDA\retinaProject\label.csv'
image_filepath = 'Image_P/'
# import library
import tensorflow as tf
import numpy as np
#=============================================================================
# Read input data
# load csv content
csv_path = tf.train.string_input_producer(['label.csv'])
textReader = tf.TextLineReader()
_, csv_content = textReader.read(csv_path)
im_name, label = tf.decode_csv(csv_content, record_defaults=[[""], [1]])
# load images
im_content = tf.read_file(image_filepath + im_name+'.jpeg')
image = tf.image.decode_jpeg(im_content, channels=3)
def label_3D (label_num):
label_3D = np.zeros(3)
if label_num == 0:
label_3D[0] = 1
else:
if label_num == 3:
label_3D[1] = 1
else: # label_num == 4
label_3D[2] = 1
return label_3D
# =============================================================================
# Construct Network(you can skip this part)
# define functions
def weight_varible(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')
# paras
W_conv1 = weight_varible([5, 5, 3, 32])
b_conv1 = bias_variable([32])
# conv layer-1
x = tf.Variable(tf.zeros([batch_size, img_width, img_height, 3]))
h_conv1 = tf.nn.relu(conv2d(x, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# conv layer-2
W_conv2 = weight_varible([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
# full connection
W_fc1 = weight_varible([16 * 16 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 16 * 16 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# dropout
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# output layer: softmax
W_fc2 = weight_varible([1024, 3])
b_fc2 = bias_variable([3])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
y_ = tf.Variable(tf.zeros([batch_size, 3]))
# model training
cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
if GradientDescentOptimizer:
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy)
else:
if AdamOptimizer:
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.arg_max(y_conv, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# ==========================================================================
# Lauch the graph
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# Start file queue
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
images, labels = sess.run([image, label])
#position1 for tf.train.shuffle_batch() function
coord.request_stop()
coord.join(threads)
for i in range(training_iters):
#position2 for tf.train.shuffle_batch() function
batch = tf.train.shuffle_batch([images,label_3D(labels)], batch_size=batch_size,
capacity = batch_size * 50,
min_after_dequeue = batch_size * 10,
num_threads = 1)
if i % display_step == 0:
x = batch[0]
y_ = batch[1]
train_accuacy = accuracy.eval()
print("step %d, training accuracy %g"%(i, train_accuacy))
x= batch[0]
y_ = batch[1]
train_step.run()
`
4.运行结果
- 在IPython控制台中
step 0, training accuracy 0.226562
step 10, training accuracy 1
step 20, training accuracy 1
step 30, training accuracy 1
step 40, training accuracy 1
- 在变异探索中
变量标签和图像不变，作为标签和图像的第一个例子，它存储在label.csv文件的第一行
因此，我推断读取文件队列已经卡在第一行，导致CNN快速收敛，准确度为1.
答案 0 :(得分：0)
shuffle_batch 接受张量并返回张量，因此它是张量流操作，应放在Graph 中。 shuffle_batch docs
我会在解码单张图片后立即放置它：
image = tf.image.decode_jpeg(im_content, channels=3)
images_batch, labels_batch = tf.train.shuffle_batch([image, label], batch_size, batch_size * 50, batch_size * 10)
# images_batch is now Tensor of shape (batch_size, height, weight, channels)
...
h_conv1 = tf.nn.relu(conv2d(images_batch, W_conv1) + b_conv1)
您现在不需要变量x和y_，并且在使用tf.train.shuffle_batch时无需手动分配输入。
tf.train.shuffle_batch接受单个示例的张量并产生整个批次可能看似违反直觉，但请记住，您提供给此操作的张量来自队列，因此tf.train.shuffle_batch可以“等待” “对于多个元素（在引擎盖下它实际上使用另一个队列来进行混洗和存储中间元素，shuffle_batch实现是here）