cifar10.py

#-*-coding:UTF-8-*-
"""Builds the CIFAR-10 network.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import re
import tensorflow as tf

import cifar10_input

data_dir = "hdfs://b10g37:8020/user/root/train_data/cifar-10-batches-bin/"
use_fp16 = False

#parameters initialize
def parameters_initialize (i_batch_size, i_learning_rate):
    batch_size = i_batch_size
    learning_rate = i_learning_rate

#get optimizer
def get_optimizer(optimizer, learning_rate):
    if optimizer == "SGD":
	return tf.train.GradientDescentOptimizer(learning_rate)
    elif optimizer == "Adadelta":
	return  tf.train.AdadeltaOptimizer(learning_rate)
    elif optimizer == "Adagrad":
	return  tf.train.AdagradOptimizer(learning_rate)
    elif optimizer == "Ftrl":
        return  tf.train.FtrlOptimizer(learning_rate)
    elif optimizer == "Adam":
	return  tf.train.AdamOptimizer(learning_rate)
    elif optimizer == "Momentum":
	return  tf.train.MomentumOptimizer(learning_rate, 0.9)
    elif optimizer == "RMSProp":
	return  tf.train.RMSPropOptimizer(learning_rate)



# Global constants describing the CIFAR-10 data set.
IMAGE_SIZE = cifar10_input.IMAGE_SIZE
NUM_CLASSES = cifar10_input.NUM_CLASSES
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = cifar10_input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = cifar10_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.

# Variables that affect learning rate.
#decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY)

# 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.summary.histogram(tensor_name + '/activations', x)
  tf.summary.scalar(tensor_name + '/sparsity',
                                       tf.nn.zero_fraction(x))


def _variable_on_cpu(name, shape, initializer, variable_partition_num):
  """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
  """
  dtype = tf.float16 if use_fp16 else tf.float32
  var = tf.get_variable(name, shape, initializer=initializer, dtype=dtype, partitioner=tf.fixed_size_partitioner(variable_partition_num))
  return var


def _variable_with_weight_decay(name, shape, stddev, wd, variable_partition_num):
  """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 use_fp16 else tf.float32
  var = _variable_on_cpu(
      name,
      shape,
      tf.truncated_normal_initializer(stddev=stddev, dtype=dtype),
      variable_partition_num)
  if wd is not None:
    weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')
    tf.add_to_collection('losses', weight_decay)
  return var


def distorted_inputs(batch_size):
  """Construct distorted input for CIFAR training using the Reader ops.
  Returns:
    images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
    labels: Labels. 1D tensor of [batch_size] size.
  Raises:
    ValueError: If no data_dir
  """
  if not data_dir:
    raise ValueError('Please supply a data_dir')
  
  images, labels = cifar10_input.distorted_inputs(data_dir=data_dir,
                                                  batch_size=batch_size)
  if use_fp16:
    images = tf.cast(images, tf.float16)
    labels = tf.cast(labels, tf.float16)
  return images, labels


def inputs(eval_data):
  """Construct input for CIFAR evaluation using the Reader ops.
  Args:
    eval_data: bool, indicating if one should use the train or eval data set.
  Returns:
    images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
    labels: Labels. 1D tensor of [batch_size] size.
  Raises:
    ValueError: If no data_dir
  """
  if not data_dir:
    raise ValueError('Please supply a data_dir')
  data_dir = os.path.join(data_dir, 'cifar-10-batches-bin')
  images, labels = cifar10_input.inputs(eval_data=eval_data,
                                        data_dir=data_dir,
                                        batch_size=batch_size)
  if use_fp16:
    images = tf.cast(images, tf.float16)
    labels = tf.cast(labels, tf.float16)
  return images, labels


def inference(images, batch_size, partition_num):
  """Build the CIFAR-10 model.
  Args:
    images: Images returned from distorted_inputs() or inputs().
  Returns:
    Logits.
  """
  # We instantiate all variables using tf.get_variable() instead of
  # tf.Variable() in order to share variables across multiple GPU training runs.
  # If we only ran this model on a single GPU, we could simplify this function
  # by replacing all instances of tf.get_variable() with tf.Variable().
  #
  # conv1
  with tf.variable_scope('conv1') as scope:
    kernel = _variable_with_weight_decay('weights',
                                         shape=[5, 5, 3, 64],
                                         stddev=5e-2,
                                         wd=0.0,
					 variable_partition_num=1)
    conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
    biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0),1)
    pre_activation = tf.nn.bias_add(conv, biases)
    conv1 = tf.nn.relu(pre_activation, 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,
					 variable_partition_num=1)
    conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
    biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.1),1)
    pre_activation = tf.nn.bias_add(conv, biases)
    conv2 = tf.nn.relu(pre_activation, 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, [batch_size, -1])
    dim = reshape.get_shape()[1].value
    weights = _variable_with_weight_decay('weights', 
					shape=[dim, 384],
                                        stddev=0.04, 
					wd=0.004, 
					variable_partition_num=partition_num)
    biases = _variable_on_cpu('biases', [384], tf.constant_initializer(0.1), 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, 
					variable_partition_num=partition_num)
    biases = _variable_on_cpu('biases', [192], tf.constant_initializer(0.1), 1)
    local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=scope.name)
    _activation_summary(local4)

  # linear layer(WX + b),
  # We don't apply softmax here because
  # tf.nn.sparse_softmax_cross_entropy_with_logits accepts the unscaled logits
  # and performs the softmax internally for efficiency.
  with tf.variable_scope('softmax_linear') as scope:
    weights = _variable_with_weight_decay('weights', [192, NUM_CLASSES],
                                          stddev=1/192.0, wd=0.0,variable_partition_num=1)
    biases = _variable_on_cpu('biases', [NUM_CLASSES],
                              tf.constant_initializer(0.0), 1)
    softmax_linear = tf.add(tf.matmul(local4, weights), biases, name=scope.name)
    _activation_summary(softmax_linear)

  return softmax_linear