Question

我正在尝试按照TensorFlow网站上的教程构建图像识别CNN。我使用this solution将RGB 256x256图像（24个类）的目录转换为TFRecords，所以现在我有两个文件 - “培训”和“验证”。我确信所有图像都是相同的大小，但是当我尝试训练我的网络时，我唯一能做的就是这个错误：

 Invalid argument: Shape mismatch in tuple component 0. Expected [65536], got [37191]

我试图找到一个解决方案，但我没有成功 - 只有一个提示，这个错误可能是由大小与网络中声明的大小不同的图像引起的，但正如我所说 - 我确定这些图像很好。

这是我的代码：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
import os

NUM_CLASSES = 24
IMAGE_SIZE = 256
IMAGE_PIXELS = IMAGE_SIZE * IMAGE_SIZE

flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('num_epochs', 2, 'Number of epochs to run trainer.')
flags.DEFINE_integer('batch_size', 100, 'Batch size.')
flags.DEFINE_string('train_dir', 'HERE_IS_MY_DATA_DIRECTORY', 'Directory with the training data.')

TRAIN_FILE = 'train'
VALIDATION_FILE = 'validation'

sess = tf.InteractiveSession()


def read_and_decode(filename_queue):
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    features = tf.parse_single_example(
    serialized_example,
        features={
        'image/buffer': tf.FixedLenFeature([], tf.string),
        'image/class/label': tf.FixedLenFeature([], tf.int64),
    })

    image = tf.decode_raw(features['image/buffer'], tf.uint8)
    image.set_shape([IMAGE_PIXELS])
    image = tf.cast(image, tf.float32)
    image = tf.cast(image, tf.float32) * (1. / 255) - 0.5
    label = tf.cast(features['image/class/label'], tf.int32)

    return image, label


def input_pipeline(train, batch_size, num_epochs):
    if not num_epochs: num_epochs = None
    filename = os.path.join(FLAGS.train_dir,TRAIN_FILE if train else VALIDATION_FILE)
    with tf.name_scope('input'):
        filename_queue = tf.train.string_input_producer([filename], num_epochs=num_epochs)
        image, label = read_and_decode(filename_queue)
        min_after_dequeue = 10000
        capacity = min_after_dequeue + 3 * batch_size
        image_batch, label_batch = tf.train.shuffle_batch(
    [image, label], batch_size=batch_size, capacity=capacity, min_after_dequeue=min_after_dequeue)
        return image_batch, label_batch


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):
  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')

#Variaveis
x, y_ = input_pipeline(train=True, batch_size=FLAGS.batch_size, num_epochs=FLAGS.num_epochs)

#Layer 1
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1, 256, 256, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#Layer 2
W_conv2 = weight_variable([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)

#layer3
W_conv3 = weight_variable([5, 5, 64, 128])
b_conv3 = bias_variable([128])
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3)

#layer4
W_conv4 = weight_variable([5, 5, 128, 256])
b_conv4 = bias_variable([256])
h_conv4 = tf.nn.relu(conv2d(h_pool3, W_conv4) + b_conv4)
h_pool4  =max_pool_2x2(h_conv4)

#Layer5
W_conv5 = weight_variable([5, 5, 256, 512])
b_conv5 = bias_variable([512])
h_conv5 = tf.nn.relu(conv2d(h_pool4, W_conv5) + b_conv5)
h_pool5  =max_pool_2x2(h_conv5)

#layer6
W_conv6 = weight_variable([5, 5, 512, 1024])
b_conv6 = bias_variable([1024])
h_conv6 = tf.nn.relu(conv2d(h_pool5, W_conv6) + b_conv6)
h_pool6  =max_pool_2x2(h_conv6)

#Densely Connected Layer
W_fc1 = weight_variable([16 * 16 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool6_flat = tf.reshape(h_pool6, [-1, 16 * 16 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool6_flat, W_fc1) + b_fc1)

#Dropout - reduz overfitting
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#Readout layer
W_fc2 = weight_variable([1024, 36])
b_fc2 = bias_variable([36])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

#Train and evaluate
cross_entropy = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(y_conv, y_))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())

coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)

for i in range(100):
  if i%10 == 0:
    train_accuracy = accuracy.eval(feed_dict={keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))
    train_step.run(feed_dict={keep_prob: 0.5})

x, y_ = input_pipeline(train=True, batch_size=FLAGS.batch_size)
print("test accuracy %g"%accuracy.eval(feed_dict={keep_prob: 1.0}))

coord.join(threads)
sess.close()

我的代码中是否有问题或者我得到错误，因为图像是RGB（在所有教程中人们使用的是灰度图像）？如果是这样，我该如何正确处理RGB图像？

我将不胜感激任何帮助。

修改

我通过使用this script创建TFRecord文件解决了这个问题，感谢所有的帮助。

TensorFlow CNN - 元组0中的形状不匹配

0 个答案: