AIHGF

网络结构之 GoogleNet(Inception V1)
GoogleNet - Going deeper with convolutions - 2014GoogleNe...
扫描右侧二维码阅读全文
04
2018/09

网络结构之 GoogleNet(Inception V1)

GoogleNet - Going deeper with convolutions - 2014

GoogleNet,即 Inception V1 网络结构,包含 9 个 Inception 结构

GoogleNet - Netscope

Inception 结构(网络宽度):

每个 Inception 结构有 4 个分支,主要包含 1x1, 3x3, 5x5 卷积核和 max pooling 操作(pooling 的步长为 1,以保持输出特征层的尺寸与卷积核输出尺寸一致). 1x1 卷积核核的作用是降维,以避免 cancatenation 操作导致特征层过深,并减少网络参数.

Tensorflow Slim 的 Inception V1 定义

Tensorflow Slim 中的 Inception V1 里采用的卷积核只有 1x1 和 3x3 两种,没有 5x5 的卷积核.

"""
Inception V1 分类网络的定义. 
"""

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

import tensorflow as tf

from nets import inception_utils

slim = tf.contrib.slim
trunc_normal = lambda stddev: tf.truncated_normal_initializer(0.0, stddev)


def inception_v1_base(inputs,
                      final_endpoint='Mixed_5c',
                      scope='InceptionV1'):
  """
  Inception V1 基础结构定义.

  参数:
  inputs: Tensor,尺寸为 [batch_size, height, width, channels].
  final_endpoint: 指定网络定义结束的节点endpoint,即网络深度. 
                          候选值: ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
                          'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
                          'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e',
                          'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c']
    scope: 可选变量作用域 variable_scope.

  返回值:
      字典,包含网络各层的激活值.

  Raises:
    ValueError: if final_endpoint is not set to one of the predefined values.
  """
  end_points = {}
  with tf.variable_scope(scope, 'InceptionV1', [inputs]):
    with slim.arg_scope(
        [slim.conv2d, slim.fully_connected],
        weights_initializer=trunc_normal(0.01)):
      with slim.arg_scope([slim.conv2d, slim.max_pool2d],
                          stride=1, padding='SAME'):
        end_point = 'Conv2d_1a_7x7'
        net = slim.conv2d(inputs, 64, [7, 7], stride=2, scope=end_point)
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points
        end_point = 'MaxPool_2a_3x3'
        net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points
        end_point = 'Conv2d_2b_1x1'
        net = slim.conv2d(net, 64, [1, 1], scope=end_point)
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points
        end_point = 'Conv2d_2c_3x3'
        net = slim.conv2d(net, 192, [3, 3], scope=end_point)
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points
        end_point = 'MaxPool_3a_3x3'
        net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_3b'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 96, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 128, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 16, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 32, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 32, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_3c'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 192, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'MaxPool_4a_3x3'
        net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_4b'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 96, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 208, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 16, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 48, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_4c'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 112, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 224, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 24, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_4d'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 256, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 24, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_4e'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 112, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 144, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 288, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_4f'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 256, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 320, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'MaxPool_5a_2x2'
        net = slim.max_pool2d(net, [2, 2], stride=2, scope=end_point)
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_5b'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 256, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 320, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0a_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points

        end_point = 'Mixed_5c'
        with tf.variable_scope(end_point):
          with tf.variable_scope('Branch_0'):
            branch_0 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1')
          with tf.variable_scope('Branch_1'):
            branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
            branch_1 = slim.conv2d(branch_1, 384, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_2'):
            branch_2 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0a_1x1')
            branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0b_3x3')
          with tf.variable_scope('Branch_3'):
            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
            branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
          net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
        end_points[end_point] = net
        if final_endpoint == end_point: return net, end_points
    raise ValueError('Unknown final endpoint %s' % final_endpoint)


def inception_v1(inputs,
                 num_classes=1000,
                 is_training=True,
                 dropout_keep_prob=0.8,
                 prediction_fn=slim.softmax,
                 spatial_squeeze=True,
                 reuse=None,
                 scope='InceptionV1',
                 global_pool=False):
  """
  Inception V1 结构的定义.

  参数:
    inputs: Tensor,尺寸为 [batch_size, height, width, channels].
    num_classes: 待预测的类别数. 如果 num_classes=0或None,则忽略 logits 层;返回 logits 层的输入特征(dropout 层前的网络层).
    is_training: 是否是训练阶段.
    dropout_keep_prob: 保留的激活值的比例.
    prediction_fn: 计算 logits 预测值输出的函数,如softmax.
    spatial_squeeze: 如果是 True, logits 的 shape 是 [B, C];
                                如果是 false,则 logits 的 shape 是 [B, 1, 1, C];
                                其中,B 是 batch_size,C 是类别数.
    reuse: 是否重用网络及网络的变量值.
               如果需要重用,则必须给定重用的 'scope'.
    scope: 可选变量作用域 variable_scope.
    global_pool: 可选 boolean 值,选择是否在 logits 网络层前使用 avgpooling 层.
                        默认值是 fasle,则采用固定窗口的 pooling 层,将 inputs 降低到 1x1.
                        inputs 越大,则 outputs 越大.
                        如果值是 true, 则任何 inputs 尺寸都 pooled 到 1x1.

  返回值:
    net: Tensor,如果 num_classes 为非零值,则返回 logits(pre-softmax activations).
           如果 num_classes 是 0 或 None,则返回 logits 网络层的 non-dropped-out 输入.
    end_points: 字典,包含网络各层的激活值.
  """
  # Final pooling and prediction
  with tf.variable_scope(scope, 'InceptionV1', [inputs], reuse=reuse) as scope:
    with slim.arg_scope([slim.batch_norm, slim.dropout],
                        is_training=is_training):
      net, end_points = inception_v1_base(inputs, scope=scope)
      with tf.variable_scope('Logits'):
        if global_pool:
          # Global average pooling.
          net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
          end_points['global_pool'] = net
        else:
          # Pooling with a fixed kernel size.
          net = slim.avg_pool2d(net, [7, 7], stride=1, scope='AvgPool_0a_7x7')
          end_points['AvgPool_0a_7x7'] = net
        if not num_classes:
          return net, end_points
        net = slim.dropout(net, dropout_keep_prob, scope='Dropout_0b')
        logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
                             normalizer_fn=None, scope='Conv2d_0c_1x1')
        if spatial_squeeze:
          logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')

        end_points['Logits'] = logits
        end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
  return logits, end_points
inception_v1.default_image_size = 224

inception_v1_arg_scope = inception_utils.inception_arg_scope
Last modification:October 9th, 2018 at 09:31 am

Leave a Comment