Demo entry 6340032

sdfasdf

   

Submitted by jint on Dec 27, 2016 at 07:49
Language: Python. Code size: 11.9 kB.

# pylint: disable=missing-docstring
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import gzip
import os
import re
import sys
import tarfile

from six.moves import urllib
import tensorflow as tf

from svhn_input import SVHN_dataset, IMAGE_SIZE, NUM_CLASSES, NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
from svhn_input import NUM_EXAMPLES_PER_EPOCH_FOR_EVAL

FLAGS = tf.app.flags.FLAGS

# Basic model parameters.
tf.app.flags.DEFINE_integer('batch_size', 64,
                            """Number of images to process in a batch.""")
tf.app.flags.DEFINE_string('data_dir', '.',
                           """Path to the CIFAR-10 data directory.""")
tf.app.flags.DEFINE_boolean('use_fp16', False,
                            """Train the model using fp16.""")

# Global constants describing the CIFAR-10 data set.
# IMAGE_SIZE = svhn_input.IMAGE_SIZE
# NUM_CLASSES = svhn_input.NUM_CLASSES
# NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = svhn_input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
# NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = svhn_input.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL


# Constants describing the training process.
MOVING_AVERAGE_DECAY = 0.9999     # The decay to use for the moving average.
NUM_EPOCHS_PER_DECAY = 350.0      # Epochs after which learning rate decays.
LEARNING_RATE_DECAY_FACTOR = 0.1  # Learning rate decay factor.
INITIAL_LEARNING_RATE = 0.1       # Initial learning rate.

# If a model is trained with multiple GPUs, prefix all Op names with tower_name
# to differentiate the operations. Note that this prefix is removed from the
# names of the summaries when visualizing a model.
TOWER_NAME = 'tower'




def _activation_summary(x):
  """Helper to create summaries for activations.

  Creates a summary that provides a histogram of activations.
  Creates a summary that measures the sparsity of activations.

  Args:
    x: Tensor
  Returns:
    nothing
  """
  # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
  # session. This helps the clarity of presentation on tensorboard.
  tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name)
  tf.histogram_summary(tensor_name + '/activations', x)
  tf.scalar_summary(tensor_name + '/sparsity', tf.nn.zero_fraction(x))


def _variable_on_cpu(name, shape, initializer):
  """Helper to create a Variable stored on CPU memory.

  Args:
    name: name of the variable
    shape: list of ints
    initializer: initializer for Variable

  Returns:
    Variable Tensor
  """
  with tf.device('/cpu:0'):
    dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
    var = tf.get_variable(name, shape, initializer=initializer, dtype=dtype)
  return var


def _variable_with_weight_decay(name, shape, stddev, wd):
  """Helper to create an initialized Variable with weight decay.

  Note that the Variable is initialized with a truncated normal distribution.
  A weight decay is added only if one is specified.

  Args:
    name: name of the variable
    shape: list of ints
    stddev: standard deviation of a truncated Gaussian
    wd: add L2Loss weight decay multiplied by this float. If None, weight
        decay is not added for this Variable.

  Returns:
    Variable Tensor
  """
  dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
  var = _variable_on_cpu(
      name,
      shape,
      tf.truncated_normal_initializer(stddev=stddev, dtype=dtype))
  if wd is not None:
    weight_decay = tf.mul(tf.nn.l2_loss(var), wd, name='weight_loss')
    tf.add_to_collection('losses', weight_decay)
  return var


def distorted_inputs():
  pass
  


def inputs(eval_data):
  pass


def inference(images):

  images = tf.map_fn(lambda img: tf.image.per_image_whitening(img), images)

  with tf.variable_scope('conv1') as scope:
    kernel = _variable_with_weight_decay('weights',
                                         shape=[5, 5, 3, 64],
                                         stddev=5e-2,
                                         wd=0.0)
    conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
    biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0))
    bias = tf.nn.bias_add(conv, biases)
    conv1 = tf.nn.relu(bias, name=scope.name)
    _activation_summary(conv1)

  # pool1
  pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
                         padding='SAME', name='pool1')
  # norm1
  norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
                    name='norm1')

  # conv2
  with tf.variable_scope('conv2') as scope:
    kernel = _variable_with_weight_decay('weights',
                                         shape=[5, 5, 64, 64],
                                         stddev=5e-2,
                                         wd=0.0)
    conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
    biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.1))
    bias = tf.nn.bias_add(conv, biases)
    conv2 = tf.nn.relu(bias, name=scope.name)
    _activation_summary(conv2)

  # norm2
  norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
                    name='norm2')
  # pool2
  pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1],
                         strides=[1, 2, 2, 1], padding='SAME', name='pool2')

  # local3
  with tf.variable_scope('local3') as scope:
    # Move everything into depth so we can perform a single matrix multiply.
    reshape = tf.reshape(pool2, [FLAGS.batch_size, -1])
    dim = reshape.get_shape()[1].value
    weights = _variable_with_weight_decay('weights', shape=[dim, 384],
                                          stddev=0.04, wd=0.004)
    biases = _variable_on_cpu('biases', [384], tf.constant_initializer(0.1))
    local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
    _activation_summary(local3)

  # local4
  with tf.variable_scope('local4') as scope:
    weights = _variable_with_weight_decay('weights', shape=[384, 192],
                                          stddev=0.04, wd=0.004)
    biases = _variable_on_cpu('biases', [192], tf.constant_initializer(0.1))
    local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=scope.name)
    _activation_summary(local4)

  # softmax, i.e. softmax(WX + b)
  with tf.variable_scope('softmax_linear') as scope:
    weights = _variable_with_weight_decay('weights', [192, NUM_CLASSES],
                                          stddev=1/192.0, wd=0.0)
    biases = _variable_on_cpu('biases', [NUM_CLASSES],
                              tf.constant_initializer(0.0))
    softmax_linear = tf.add(tf.matmul(local4, weights), biases, name=scope.name)
    _activation_summary(softmax_linear)

  return softmax_linear


def loss(logits, labels):
  """Add L2Loss to all the trainable variables.

  Add summary for "Loss" and "Loss/avg".
  Args:
    logits: Logits from inference().
    labels: Labels from distorted_inputs or inputs(). 1-D tensor
            of shape [batch_size]

  Returns:
    Loss tensor of type float.
  """
  # Calculate the average cross entropy loss across the batch.
  labels = tf.cast(labels, tf.int64)
  cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
      logits, labels, name='cross_entropy_per_example')
  cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
  tf.add_to_collection('losses', cross_entropy_mean)

  # The total loss is defined as the cross entropy loss plus all of the weight
  # decay terms (L2 loss).
  return tf.add_n(tf.get_collection('losses'), name='total_loss')


def _add_loss_summaries(total_loss):
  """Add summaries for losses in CIFAR-10 model.

  Generates moving average for all losses and associated summaries for
  visualizing the performance of the network.

  Args:
    total_loss: Total loss from loss().
  Returns:
    loss_averages_op: op for generating moving averages of losses.
  """
  # Compute the moving average of all individual losses and the total loss.
  loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
  losses = tf.get_collection('losses')
  loss_averages_op = loss_averages.apply(losses + [total_loss])

  # Attach a scalar summary to all individual losses and the total loss; do the
  # same for the averaged version of the losses.
  for l in losses + [total_loss]:
    # Name each loss as '(raw)' and name the moving average version of the loss
    # as the original loss name.
    tf.scalar_summary(l.op.name +' (raw)', l)
    tf.scalar_summary(l.op.name, loss_averages.average(l))

  return loss_averages_op


def train(total_loss, global_step):
  """Train CIFAR-10 model.

  Create an optimizer and apply to all trainable variables. Add moving
  average for all trainable variables.

  Args:
    total_loss: Total loss from loss().
    global_step: Integer Variable counting the number of training steps
      processed.
  Returns:
    train_op: op for training.
  """
  # Variables that affect learning rate.
  num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size
  decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY)

  # Decay the learning rate exponentially based on the number of steps.
  lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE,
                                  global_step,
                                  decay_steps,
                                  LEARNING_RATE_DECAY_FACTOR,
                                  staircase=True)
  tf.scalar_summary('learning_rate', lr)

  # Generate moving averages of all losses and associated summaries.
  loss_averages_op = _add_loss_summaries(total_loss)

  # Compute gradients.
  with tf.control_dependencies([loss_averages_op]):
    opt = tf.train.GradientDescentOptimizer(lr)
    grads = opt.compute_gradients(total_loss)

  # Apply gradients.
  apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)

  # Add histograms for trainable variables.
  for var in tf.trainable_variables():
    tf.histogram_summary(var.op.name, var)

  # Add histograms for gradients.
  for grad, var in grads:
    if grad is not None:
      tf.histogram_summary(var.op.name + '/gradients', grad)

  # Track the moving averages of all trainable variables.
  variable_averages = tf.train.ExponentialMovingAverage(
      MOVING_AVERAGE_DECAY, global_step)
  variables_averages_op = variable_averages.apply(tf.trainable_variables())

  with tf.control_dependencies([apply_gradient_op, variables_averages_op]):
    train_op = tf.no_op(name='train')

  return train_op


def maybe_download_and_extract(train_or_test='train'):
  """Download and extract the tarball from The Street View House Numbers (SVHN) Dataset:
     http://ufldl.stanford.edu/housenumbers/."""
  TRAIN_DATA_URL = 'http://ufldl.stanford.edu/housenumbers/train_32x32.mat'
  TEST_DATA_URL = 'http://ufldl.stanford.edu/housenumbers/test_32x32.mat'
  train_filename = TRAIN_DATA_URL.split('/')[-1]
  test_filename = TEST_DATA_URL.split('/')[-1]

  # print(os.path.dirname(__file__))
  cur_directory = os.path.dirname(__file__)
  train_filepath = os.path.join(cur_directory, train_filename)
  test_filepath = os.path.join(cur_directory, test_filename)

  def _download(filepath, filename, data_url):
    if not os.path.exists(filepath):
      def _progress(count, block_size, total_size):
        sys.stdout.write('\r>> Downloading %s %.1f%%' % (filename,
            float(count * block_size) / float(total_size) * 100.0))
        sys.stdout.flush()
      filepath, _ = urllib.request.urlretrieve(data_url, filepath, _progress)
      print()
      statinfo = os.stat(filepath)
      print('Successfully downloaded', filename, statinfo.st_size, 'bytes.')
      # tarfile.open(filepath, 'r:gz').extractall(dest_directory)

  if train_or_test == 'train':
    _download(train_filepath, train_filename, TRAIN_DATA_URL )
  else:
    _download(test_filepath,test_filename, TEST_DATA_URL )

This snippet took 0.01 seconds to highlight.

Back to the Entry List or Home.

Delete this entry (admin only).