PROSAGA码农传奇-测试训练-在Tensorflow中运行CNN时的训练和测试的奇怪值

<div class =“post-text”itemprop =“text”>
  
    sinc我不能遵循你的代码。这里是一个使用Tensorflow的完整转换层脚本的示例。
  
  
    的
      1
    </强>
    
如果您正在使用图像，那么序列化您的数据卷积操作确实有意义！
以下脚本以TFrecords格式序列化您的图像。 [基于Inception示例]。
  
   <pre>
 <code>
 '''
Converts image data to TFRecords file format with Example protos.
The image data set is expected to reside in JPEG files located in the
following directory structure.
 trainingset/label_0/image0.jpeg
 trainingset/label_0/image1.jpg
 ...
 testset/label_1/weird-image.jpeg
 testset/label_1/my-image.jpeg
'''

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

from datetime import datetime
import os
import random
import sys
import threading

import numpy as np
import tensorflow as tf

tf.app.flags.DEFINE_string('train_directory', '/tmp/',
                           'Training data directory')
tf.app.flags.DEFINE_string('validation_directory', '/tmp/',
                           'Validation data directory')
tf.app.flags.DEFINE_string('output_directory', '/tmp/',
                           'Output data directory')

tf.app.flags.DEFINE_integer('train_shards', 2,
                            'Number of shards in training TFRecord files.')
tf.app.flags.DEFINE_integer('validation_shards', 2,
                            'Number of shards in validation TFRecord files.')

tf.app.flags.DEFINE_integer('num_threads', 2,
                            'Number of threads to preprocess the images.')

# The labels file contains a list of valid labels are held in this file.
# Assumes that the file contains entries as such:
#   dog
#   cat
#   flower
# where each line corresponds to a label. We map each label contained in
# the file to an integer corresponding to the line number starting from 0.
tf.app.flags.DEFINE_string('labels_file', '', 'Labels file')

FLAGS = tf.app.flags.FLAGS

def _int64_feature(value):
  """Wrapper for inserting int64 features into Example proto."""
  if not isinstance(value, list):
    value = [value]
  return tf.train.Feature(int64_list=tf.train.Int64List(value=value))

def _bytes_feature(value):
  """Wrapper for inserting bytes features into Example proto."""
  return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

def _convert_to_example(filename, image_buffer, label, text, height, width):
  """Build an Example proto for an example.
  Args:
    filename: string, path to an image file, e.g., '/path/to/example.JPG'
    image_buffer: string, JPEG encoding of RGB image
    label: integer, identifier for the ground truth for the network
    text: string, unique human-readable, e.g. 'dog'
    height: integer, image height in pixels
    width: integer, image width in pixels
  Returns:
    Example proto
  """

colorspace = 'RGB'
  channels = 3
  image_format = 'JPEG'

example = tf.train.Example(features=tf.train.Features(feature={
      'image/height': _int64_feature(height),
      'image/width': _int64_feature(width),
      'image/colorspace': _bytes_feature(tf.compat.as_bytes(colorspace)),
      'image/channels': _int64_feature(channels),
      'image/class/label': _int64_feature(label),
      'image/class/text': _bytes_feature(tf.compat.as_bytes(text)),
      'image/format': _bytes_feature(tf.compat.as_bytes(image_format)),
      'image/filename': _bytes_feature(tf.compat.as_bytes(os.path.basename(filename))),
      'image/encoded': _bytes_feature(tf.compat.as_bytes(image_buffer))}))
  return example

class ImageCoder(object):
  """Helper class that provides TensorFlow image coding utilities."""

def __init__(self):
    # Create a single Session to run all image coding calls.
    self._sess = tf.Session()

# Initializes function that converts PNG to JPEG data.
    self._png_data = tf.placeholder(dtype=tf.string)
    image = tf.image.decode_png(self._png_data, channels=3)
    self._png_to_jpeg = tf.image.encode_jpeg(image, format='rgb', quality=100)

# Initializes function that decodes RGB JPEG data.
    self._decode_jpeg_data = tf.placeholder(dtype=tf.string)
    self._decode_jpeg = tf.image.decode_jpeg(self._decode_jpeg_data, channels=3)

def png_to_jpeg(self, image_data):
    return self._sess.run(self._png_to_jpeg,
                          feed_dict={self._png_data: image_data})

def decode_jpeg(self, image_data):
    image = self._sess.run(self._decode_jpeg,
                           feed_dict={self._decode_jpeg_data: image_data})
    assert len(image.shape) == 3
    assert image.shape[2] == 3
    return image

def _is_png(filename):
  """Determine if a file contains a PNG format image.
  Args:
    filename: string, path of the image file.
  Returns:
    boolean indicating if the image is a PNG.
  """
  return '.png' in filename

def _process_image(filename, coder):
  """Process a single image file.
  Args:
    filename: string, path to an image file e.g., '/path/to/example.JPG'.
    coder: instance of ImageCoder to provide TensorFlow image coding utils.
  Returns:
    image_buffer: string, JPEG encoding of RGB image.
    height: integer, image height in pixels.
    width: integer, image width in pixels.
  """
  # Read the image file.
  with tf.gfile.FastGFile(filename, 'rb') as f:
    image_data = f.read()

# Convert any PNG to JPEG's for consistency.
  if _is_png(filename):
    print('Converting PNG to JPEG for %s' % filename)
    image_data = coder.png_to_jpeg(image_data)

# Decode the RGB JPEG.
  image = coder.decode_jpeg(image_data)

# Check that image converted to RGB
  assert len(image.shape) == 3
  height = image.shape[0]
  width = image.shape[1]
  assert image.shape[2] == 3

return image_data, height, width

def _process_image_files_batch(coder, thread_index, ranges, name, filenames,
                               texts, labels, num_shards):
  """Processes and saves list of images as TFRecord in 1 thread.
  Args:
    coder: instance of ImageCoder to provide TensorFlow image coding utils.
    thread_index: integer, unique batch to run index is within [0, len(ranges)).
    ranges: list of pairs of integers specifying ranges of each batches to
      analyze in parallel.
    name: string, unique identifier specifying the data set
    filenames: list of strings; each string is a path to an image file
    texts: list of strings; each string is human readable, e.g. 'dog'
    labels: list of integer; each integer identifies the ground truth
    num_shards: integer number of shards for this data set.
  """
  # Each thread produces N shards where N = int(num_shards / num_threads).
  # For instance, if num_shards = 128, and the num_threads = 2, then the first
  # thread would produce shards [0, 64).
  num_threads = len(ranges)
  assert not num_shards % num_threads
  num_shards_per_batch = int(num_shards / num_threads)

shard_ranges = np.linspace(ranges[thread_index][0],
                             ranges[thread_index][1],
                             num_shards_per_batch + 1).astype(int)
  num_files_in_thread = ranges[thread_index][1] - ranges[thread_index][0]

counter = 0
  for s in range(num_shards_per_batch):
    # Generate a sharded version of the file name, e.g. 'train-00002-of-00010'
    shard = thread_index * num_shards_per_batch + s
    output_filename = '%s-%.5d-of-%.5d' % (name, shard, num_shards)
    output_file = os.path.join(FLAGS.output_directory, output_filename)
    writer = tf.python_io.TFRecordWriter(output_file)

shard_counter = 0
    files_in_shard = np.arange(shard_ranges[s], shard_ranges[s + 1], dtype=int)
    for i in files_in_shard:
      filename = filenames[i]
      label = labels[i]
      text = texts[i]

try:
        image_buffer, height, width = _process_image(filename, coder)
      except Exception as e:
        print(e)
        print('SKIPPED: Unexpected eror while decoding %s.' % filename)
        continue

example = _convert_to_example(filename, image_buffer, label,
                                    text, height, width)
      writer.write(example.SerializeToString())
      shard_counter += 1
      counter += 1

if not counter % 1000:
        print('%s [thread %d]: Processed %d of %d images in thread batch.' %
              (datetime.now(), thread_index, counter, num_files_in_thread))
        sys.stdout.flush()

writer.close()
    print('%s [thread %d]: Wrote %d images to %s' %
          (datetime.now(), thread_index, shard_counter, output_file))
    sys.stdout.flush()
    shard_counter = 0
  print('%s [thread %d]: Wrote %d images to %d shards.' %
        (datetime.now(), thread_index, counter, num_files_in_thread))
  sys.stdout.flush()

def _process_image_files(name, filenames, texts, labels, num_shards):
  """Process and save list of images as TFRecord of Example protos.
  Args:
    name: string, unique identifier specifying the data set
    filenames: list of strings; each string is a path to an image file
    texts: list of strings; each string is human readable, e.g. 'dog'
    labels: list of integer; each integer identifies the ground truth
    num_shards: integer number of shards for this data set.
  """
  assert len(filenames) == len(texts)
  assert len(filenames) == len(labels)

# Break all images into batches with a [ranges[i][0], ranges[i][1]].
  spacing = np.linspace(0, len(filenames), FLAGS.num_threads + 1).astype(np.int)
  ranges = []
  for i in range(len(spacing) - 1):
    ranges.append([spacing[i], spacing[i + 1]])

# Launch a thread for each batch.
  print('Launching %d threads for spacings: %s' % (FLAGS.num_threads, ranges))
  sys.stdout.flush()

# Create a mechanism for monitoring when all threads are finished.
  coord = tf.train.Coordinator()

# Create a generic TensorFlow-based utility for converting all image codings.
  coder = ImageCoder()

threads = []
  for thread_index in range(len(ranges)):
    args = (coder, thread_index, ranges, name, filenames,
            texts, labels, num_shards)
    t = threading.Thread(target=_process_image_files_batch, args=args)
    t.start()
    threads.append(t)

# Wait for all the threads to terminate.
  coord.join(threads)
  print('%s: Finished writing all %d images in data set.' %
        (datetime.now(), len(filenames)))
  sys.stdout.flush()

def _find_image_files(data_dir, labels_file):
  """Build a list of all images files and labels in the data set.
  Args:
    data_dir: string, path to the root directory of images.
      Assumes that the image data set resides in JPEG files located in
      the following directory structure.
        data_dir/dog/another-image.JPEG
        data_dir/dog/my-image.jpg
      where 'dog' is the label associated with these images.
    labels_file: string, path to the labels file.
      The list of valid labels are held in this file. Assumes that the file
      contains entries as such:
        dog
        cat
        flower
      where each line corresponds to a label. We map each label contained in
      the file to an integer starting with the integer 0 corresponding to the
      label contained in the first line.
  Returns:
    filenames: list of strings; each string is a path to an image file.
    texts: list of strings; each string is the class, e.g. 'dog'
    labels: list of integer; each integer identifies the ground truth.
  """
  print('Determining list of input files and labels from %s.' % data_dir)
  unique_labels = [l.strip() for l in tf.gfile.FastGFile(
      labels_file, 'r').readlines()]

labels = []
  filenames = []
  texts = []

# Leave label index 0 empty as a background class.
  label_index = 1

# Construct the list of JPEG files and labels.
  for text in unique_labels:
    jpeg_file_path = '%s/%s/*' % (data_dir, text)
    matching_files = tf.gfile.Glob(jpeg_file_path)

labels.extend([label_index] * len(matching_files))
    texts.extend([text] * len(matching_files))
    filenames.extend(matching_files)

if not label_index % 100:
      print('Finished finding files in %d of %d classes.' % (
          label_index, len(labels)))
    label_index += 1

# Shuffle the ordering of all image files in order to guarantee
  # random ordering of the images with respect to label in the
  # saved TFRecord files. Make the randomization repeatable.
  shuffled_index = list(range(len(filenames)))
  random.seed(12345)
  random.shuffle(shuffled_index)

filenames = [filenames[i] for i in shuffled_index]
  texts = [texts[i] for i in shuffled_index]
  labels = [labels[i] for i in shuffled_index]

print('Found %d JPEG files across %d labels inside %s.' %
        (len(filenames), len(unique_labels), data_dir))
  return filenames, texts, labels

def _process_dataset(name, directory, num_shards, labels_file):
  """Process a complete data set and save it as a TFRecord.
  Args:
    name: string, unique identifier specifying the data set.
    directory: string, root path to the data set.
    num_shards: integer number of shards for this data set.
    labels_file: string, path to the labels file.
  """
  filenames, texts, labels = _find_image_files(directory, labels_file)
  _process_image_files(name, filenames, texts, labels, num_shards)

def main(unused_argv):
  assert not FLAGS.train_shards % FLAGS.num_threads, (
      'Please make the FLAGS.num_threads commensurate with FLAGS.train_shards')
  assert not FLAGS.validation_shards % FLAGS.num_threads, (
      'Please make the FLAGS.num_threads commensurate with '
      'FLAGS.validation_shards')
  print('Saving results to %s' % FLAGS.output_directory)

# Run it!
  _process_dataset('validation', FLAGS.validation_directory,
                   FLAGS.validation_shards, FLAGS.labels_file)
  _process_dataset('train', FLAGS.train_directory,
                   FLAGS.train_shards, FLAGS.labels_file)

if __name__ == '__main__':
  tf.app.run()

</code>
 </pre>
  
    你需要启动脚本如下：
  
   <pre>
 <code>
 python Building_Set.py --train_directory=TrainingSet --output_directory=TF_Recordsfolder --validation_directory=ReferenceSet --labels_file=labels.txt --train_shards=1 --validation_shards=1 --num_threads=1

</code>
 </pre>
  
    PS：你需要一个
     <code>
 labels.txt
 </code>
     标签保存的位置。
  
  
    生成训练集和测试集序列化文件后，您现在可以使用以下convNN脚本中的数据：
  
   <pre>
 <code>
 import tensorflow as tf
import sys
import numpy as np
import matplotlib.pyplot as plt
filter_max_dimension = 50
filter_max_depth = 30
filter_h_and_w = [3,3]
filter_depth = [3,3]
numberOFclasses = 21
TensorBoard = "TB_conv2NN"
TF_Records = "TF_Recordsfolder"
learning_rate = 1e-5
max_numberofiteretion =100000
batchSize = 21
img_height = 128
img_width = 128

# 1st function to read images form TF_Record
def getImage(filename):
    with tf.device('/cpu:0'):
        # convert filenames to a queue for an input pipeline.
        filenameQ = tf.train.string_input_producer([filename],num_epochs=None)

# object to read records
        recordReader = tf.TFRecordReader()

# read the full set of features for a single example
        key, fullExample = recordReader.read(filenameQ)

# parse the full example into its' component features.
        features = tf.parse_single_example(
            fullExample,
            features={
                'image/height': tf.FixedLenFeature([], tf.int64),
                'image/width': tf.FixedLenFeature([], tf.int64),
                'image/colorspace': tf.FixedLenFeature([], dtype=tf.string,default_value=''),
                'image/channels':  tf.FixedLenFeature([], tf.int64),
                'image/class/label': tf.FixedLenFeature([],tf.int64),
                'image/class/text': tf.FixedLenFeature([], dtype=tf.string,default_value=''),
                'image/format': tf.FixedLenFeature([], dtype=tf.string,default_value=''),
                'image/filename': tf.FixedLenFeature([], dtype=tf.string,default_value=''),
                'image/encoded': tf.FixedLenFeature([], dtype=tf.string, default_value='')
            })

# now we are going to manipulate the label and image features
        label = features['image/class/label']
        image_buffer = features['image/encoded']
        # Decode the jpeg
        with tf.name_scope('decode_img',[image_buffer], None):
            # decode
            image = tf.image.decode_jpeg(image_buffer, channels=3)

# and convert to single precision data type
            image = tf.image.convert_image_dtype(image, dtype=tf.float32)
        # cast image into a single array, where each element corresponds to the greyscale
        # value of a single pixel.
        # the "1-.." part inverts the image, so that the background is black.
        image=tf.reshape(1-tf.image.rgb_to_grayscale(image),[img_height*img_width])
        # re-define label as a "one-hot" vector
        # it will be [0,1] or [1,0] here.
        # This approach can easily be extended to more classes.
        label=tf.stack(tf.one_hot(label-1, numberOFclasses))
        return label, image

with tf.device('/cpu:0'):
    train_img,train_label = getImage(TF_Records+"/train-00000-of-00001")
    validation_img,validation_label=getImage(TF_Records+"/validation-00000-of-00001")
    # associate the "label_batch" and "image_batch" objects with a randomly selected batch---
    # of labels and images respectively
    train_imageBatch, train_labelBatch = tf.train.shuffle_batch([train_img, train_label], batch_size=batchSize,capacity=50,min_after_dequeue=10)

# and similarly for the validation data
    validation_imageBatch, validation_labelBatch = tf.train.shuffle_batch([validation_img, validation_label],
                                                    batch_size=batchSize,capacity=50,min_after_dequeue=10)

def train():
    with tf.device('/gpu:0'):
        config =tf.ConfigProto(log_device_placement=False, allow_soft_placement=True)
        #config.gpu_options.allow_growth = True
        #config.gpu_options.per_process_gpu_memory_fraction=0.9
        sess = tf.InteractiveSession(config = config)
        #defining tensorflow graph :
        with tf.name_scope("input"):
            x = tf.placeholder(tf.float32,[None, img_width*img_height],name ="pixels_values")
            y_= tf.placeholder(tf.float32,[None,numberOFclasses],name='Prediction')
        with tf.name_scope("input_reshape"):
            image_shaped =tf.reshape(x,[-1,img_height,img_width,1])
            tf.summary.image('input_img',image_shaped,numberOFclasses)
        #defining weigths and biases:
        def weights_variable (shape):
            return tf.Variable(tf.truncated_normal(shape,stddev=0.1))
        def bias_variable(shape):
            return tf.Variable(tf.constant(0.1,shape=shape))
        #help function to generates summaries for given variables
        def variable_summaries(var):
            with tf.name_scope('summaries'):
                mean = tf.reduce_mean(var)
                tf.summary.scalar('mean', mean)
                with tf.name_scope('stddev'):
                    stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
                tf.summary.scalar('stddev', stddev)
                tf.summary.scalar('max', tf.reduce_max(var))
                tf.summary.scalar('min', tf.reduce_min(var))
                tf.summary.histogram('histogram', var)

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')

with tf.name_scope('1st_conv_layer'):
                W_conv1 = weights_variable([filter_h_and_w[0],filter_h_and_w[0], 1, filter_depth[0]])
                b_conv1 = bias_variable([filter_depth[0]])
                h_conv1 = tf.nn.relu(conv2d(tf.reshape(x,[-1,img_width,img_height,1]), W_conv1) + b_conv1)
            with tf.name_scope('1nd_Pooling_layer'):
                h_conv1 = max_pool_2x2(h_conv1)
            with tf.name_scope('2nd_conv_layer'):
                W_conv2 = weights_variable([filter_h_and_w[1],filter_h_and_w[1], filter_depth[0], filter_depth[1]])
                b_conv2 = bias_variable([filter_depth[1]])
                h_conv2 = tf.nn.relu(conv2d(h_conv1, W_conv2) + b_conv2)

with tf.name_scope('1st_Full_connected_Layer'):
            W_fc1 = weights_variable([filter_depth[1]*64, 1024])
            b_fc1 = bias_variable([1024])
            h_pool_flat = tf.reshape(h_conv2, [-1,filter_depth[1]*64])
            h_fc1 = tf.nn.relu(tf.matmul(h_pool_flat, W_fc1) + b_fc1)

with tf.name_scope('Dropout'):
            keep_prob = tf.placeholder("float")
            h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

with tf.name_scope('Output_layer'):
            W_fc3 = weights_variable([1024, numberOFclasses])
            b_fc3 = bias_variable([numberOFclasses])
            y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc3) + b_fc3)

with tf.name_scope('cross_entropy'):
        # The raw formulation of cross-entropy,
        #
        # tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.softmax(y)),
        #                               reduction_indices=[1]))
        #
        # can be numerically unstable.
        #
        # So here we use tf.nn.softmax_cross_entropy_with_logits on the
        # raw outputs of the nn_layer above, and then average across
        # the batch.
            diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)
            with tf.name_scope('total'):
              cross_entropy = tf.reduce_mean(diff)
        tf.summary.scalar('cross_entropy', cross_entropy)

with tf.name_scope('train'):
          train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)

with tf.name_scope('accuracy'):
            with tf.name_scope('correct_prediction'):
              correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
            with tf.name_scope('accuracy'):
              accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        tf.summary.scalar('accuracy', accuracy)
        # Merging Summaries
        merged = tf.summary.merge_all()
        train_writer = tf.summary.FileWriter(TensorBoard + '/train', sess.graph)
        test_writer = tf.summary.FileWriter(TensorBoard + '/test')
        # initialize the variables
        sess.run(tf.global_variables_initializer())

# start the threads used for reading files
        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(sess=sess,coord=coord)

# feeding function
        def feed_dict(train):
            if True :
                #img_batch, labels_batch= tf.train.shuffle_batch([train_label,train_img],batch_size=batchSize,capacity=500,min_after_dequeue=200)
                img_batch , labels_batch = sess.run([ train_labelBatch ,train_imageBatch])
                dropoutValue = 0.7
            else:
                #   img_batch,labels_batch = tf.train.shuffle_batch([validation_label,validation_img],batch_size=batchSize,capacity=500,min_after_dequeue=200)
                img_batch,labels_batch = sess.run([ validation_labelBatch,validation_imageBatch])
                dropoutValue = 1
            return {x:img_batch,y_:labels_batch,keep_prob:dropoutValue}

for i  in range(max_numberofiteretion):
            if i%10 == 0:#Run a Test
                summary, acc = sess.run([merged,accuracy],feed_dict=feed_dict(False))
                #plt.imshow(output[0,:,:,1],cmap='gray')
                #plt.show()
                test_writer.add_summary(summary,i)# Save to TensorBoard
            else: # Training
              if i % 100 == 99:  # Record execution stats
                run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
                run_metadata = tf.RunMetadata()
                summary, _ = sess.run([merged, train_step],
                                      feed_dict=feed_dict(True),
                                      options=run_options,
                                      run_metadata=run_metadata)
                train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
                train_writer.add_summary(summary, i)
              else:  # Record a summary
                output , summary, _ = sess.run([h_conv1,merged, train_step], feed_dict=feed_dict(True))
                train_writer.add_summary(summary, i)
        # finalise
        coord.request_stop()
        coord.join(threads)
        train_writer.close()
        test_writer.close()

filter_h_and_w[0] = np.random.randint(3, filter_max_dimension)
filter_h_and_w[1] = np.random.randint(3, filter_max_dimension)
filter_depth[0] = np.random.randint(3, filter_max_depth)
filter_depth[1] = np.random.randint(3, filter_max_depth)
TensorBoard = "ConV2NN/_filter"+str(filter_h_and_w[0])+"To"+str(filter_h_and_w[1])+"D"+str(filter_depth[0])+"To"+str(filter_depth[1])+"R10e5"

with tf.device('/gpu:0') :
        train()

</code>
 </pre>
  
    如果您没有GPU TF将使用您的设备的CPU，该脚本使用GPU和CPU。代码是自我解释，你需要改变图像分辨率值和类的数量。并且你需要启动Tensorboard，脚本是保存测试和训练文件夹for tensorboard你只需要在浏览器中启动它。
因为你只有2个课程我认为两个转换层就足够了，如果你认为你需要更多，那么添加它们就很容易了。
我希望这个能帮上忙
  
</DIV>