今天对照Tensorflow的书,实现了Inception Net。在Inception Net实际应用时,是基于ImageNet的。考虑到耗时,在本篇博客(甚至是在Tensorflow的书中),只计算每个batch的前馈计算(Forward)。
Inception Net最大的几个特点:
1. 使用了分支结构,并使用concat将分支结合在一起
2. 使用1X1的卷积,可以低成本的将特征进行跨通道的组合
3. 使用Batch Normalization(BN),对每个batch的数据进行标准化处理,使输出规范到N(0, 1)的正态分布
代码如下:
from datetime import datetime
import time
import math
import tensorflow as tf
# slim是一个使构建,训练,评估神经网络变得简单的库,相当于模板
slim = tf.contrib.slim
# 用lambda定义一个简单的函数,产生截断的正态分布
trunc_normal = lambda stddev: tf.truncated_normal_initializer(0.0, stddev)
# 用来生成网络中经常用到的函数的默认参数,比如卷积的激活函数、标准化器等
# moving_vars用以完成平均滑动
def inception_v3_arg_scope(weight_decay=0.00004,
stddev=0.1,
batch_norm_var_collection='moving_vars'):
# 用以使输出保持分布相同
batch_norm_params = {
'decay': 0.9997,
'epsilon': 0.001,
'updates_collections': tf.GraphKeys.UPDATE_OPS,
'variables_collections': {
'beta': None,
'gamma': None,
'moving_mean': [batch_norm_var_collection],
'moving_variance': [batch_norm_var_collection],
}
}
with slim.arg_scope([slim.conv2d, slim.fully_connected],
weights_regularizer=slim.l2_regularizer(weight_decay)):
with slim.arg_scope(
[slim.conv2d],
weights_initializer=tf.truncated_normal_initializer(stddev=stddev),
activation_fn=tf.nn.relu,
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params) as sc:
return sc
# 用以生成网络的卷积部分
def inception_v3_base(inputs, scope=None):
# 用来保存某些关键节点以供之后使用
end_points = {}
# 为slim.conv2d,slim.max_pool2d,slim.avg_pool2d三个函数设置默认的stride,padding参数值
with tf.variable_scope(scope, 'InceptionV3', [inputs]):
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='VALID'):
# conv2d(输入的tensor, 通道数, 卷积核尺寸, 步长, padding模式)
net = slim.conv2d(inputs, 32, [3, 3], stride=2, scope='Conv2d_1a_3X3')
net = slim.conv2d(net, 32, [3, 3], scope='Conv2d_2a_3X3')
net = slim.conv2d(net, 64, [3, 3], padding='SAME',
scope='Conv2d_2b_3X3')
net = slim.max_pool2d(net, [3, 3], stride=2, scope='MaxPool_3a_3X3')
# 1X1的卷积核可以低成本的将特征进行跨通道组合
net = slim.conv2d(net, 80, [1, 1], scope='Conv2d_3b_1X1')
net = slim.conv2d(net, 192, [3, 3], scope='Conv2d_4a_3X3')
net = slim.max_pool2d(net, [3, 3], stride=2, scope='MaxPool_5a_3X3')
# 第一个inception模块组
# 第一个inception module
# 最后通过concat将四个分支合并
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='SAME'):
with tf.variable_scope('Mixed_5b'):
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, 48, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = slim.conv2d(branch_1, 64, [5, 5],
scope='Conv2d_0b_5X5')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 96, [3, 3],
scope='Conv2d_0b_3X3')
branch_2 = slim.conv2d(branch_2, 96, [3, 3],
scope='Conv2d_0c_3X3')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 32, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 第二个inception module
with tf.variable_scope('Mixed_5c'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0b_1X1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0b_1X1')
branch_1 = slim.conv2d(branch_1, 64, [5, 5],
scope='Conv2d_0c_5X5')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 96, [3, 3],
scope='Conv2d_0b_3X3')
branch_2 = slim.conv2d(branch_2, 96, [3, 3],
scope='Conv2d_0c_3X3')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 第三个inception module
with tf.variable_scope('Mixed_5d'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0b_1X1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0b_1X1')
branch_1 = slim.conv2d(branch_1, 64, [5, 5],
scope='Conv2d_0c_5X5')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 96, [3, 3],
scope='Conv2d_0b_3X3')
branch_2 = slim.conv2d(branch_2, 96, [3, 3],
scope='Conv2d_0c_3X3')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 第二个inception模块组
# 第一个inception module
with tf.variable_scope('Mixed_6a'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 384, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_1X1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = slim.conv2d(branch_1, 96, [3, 3],
scope='Conv2d_0b_3X3')
branch_1 = slim.conv2d(branch_1, 96, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_1X1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID',
scope='MaxPool_1a_3X3')
net = tf.concat([branch_0, branch_1, branch_2], 3)
# 第二个inception module
with tf.variable_scope('Mixed_6b'):
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, 128, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = slim.conv2d(branch_1, 128, [1, 7],
scope='Conv2d_0b_1X7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1],
scope='Conv2d_0c_7X1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 128, [7, 1],
scope='Conv2d_0b_7X1')
branch_2 = slim.conv2d(branch_2, 128, [1, 7],
scope='Conv2d_0c_1X7')
branch_2 = slim.conv2d(branch_2, 128, [7, 1],
scope='Conv2d_0d_7X1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7],
scope='Conv2d_0e_1X7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 第三个inception module
with tf.variable_scope('Mixed_6c'):
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, 160, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = slim.conv2d(branch_1, 128, [1, 7],
scope='Conv2d_0b_1X7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1],
scope='Conv2d_0c_7X1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 160, [7, 1],
scope='Conv2d_0b_7X1')
branch_2 = slim.conv2d(branch_2, 160, [1, 7],
scope='Conv2d_0c_1X7')
branch_2 = slim.conv2d(branch_2, 160, [7, 1],
scope='Conv2d_0d_7X1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7],
scope='Conv2d_0e_1X7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 第四个inception module
with tf.variable_scope('Mixed_6d'):
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, 160, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = slim.conv2d(branch_1, 128, [1, 7],
scope='Conv2d_0b_1X7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1],
scope='Conv2d_0c_7X1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 160, [7, 1],
scope='Conv2d_0b_7X1')
branch_2 = slim.conv2d(branch_2, 160, [1, 7],
scope='Conv2d_0c_1X7')
branch_2 = slim.conv2d(branch_2, 160, [7, 1],
scope='Conv2d_0d_7X1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7],
scope='Conv2d_0e_1X7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 第五个inception module
with tf.variable_scope('Mixed_6e'):
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, 160, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = slim.conv2d(branch_1, 128, [1, 7],
scope='Conv2d_0b_1X7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1],
scope='Conv2d_0c_7X1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 160, [7, 1],
scope='Conv2d_0b_7X1')
branch_2 = slim.conv2d(branch_2, 160, [1, 7],
scope='Conv2d_0c_1X7')
branch_2 = slim.conv2d(branch_2, 160, [7, 1],
scope='Conv2d_0d_7X1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7],
scope='Conv2d_0e_1X7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points['Mixed_6e'] = net
# 第三个inception模块组
# 第一个inception module
with tf.variable_scope('Mixed_7a'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1X1')
branch_0 = slim.conv2d(branch_0, 320, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_3X3')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = slim.conv2d(branch_1, 192, [1, 7],
scope='Conv2d_0b_1X7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1],
scope='Conv2d_0c_7X1')
branch_1 = slim.conv2d(branch_1, 192, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_3X3')
with tf.variable_scope('Branch_2'):
branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID',
scope='MaxPool_1a_3X3')
net = tf.concat([branch_0, branch_1, branch_2], 3)
# 第二个inception module
with tf.variable_scope('Mixed_7b'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 320, [1, 1], scope='Conv2d_0a_1X1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = tf.concat([
slim.conv2d(branch_1, 384, [1, 3], scope='Conv2d_0b_1X3'),
slim.conv2d(branch_1, 384, [3, 1], scope='Conv2d_0b_3X1')
], 3)
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 448, [1, 3], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 384, [3, 3],
scope='Conv2d_0b_3X3')
branch_2 = tf.concat([
slim.conv2d(branch_2, 384, [1, 3], scope='Conv2d_0c_1X3'),
slim.conv2d(branch_2, 384, [3, 1], scope='Conv2d_0d_3X1')
], 3)
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 第三个inception module
with tf.variable_scope('Mixed_7c'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 320, [1, 1], scope='Conv2d_0a_1X1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1X1')
branch_1 = tf.concat([
slim.conv2d(branch_1, 384, [1, 3], scope='Conv2d_0b_1X3'),
slim.conv2d(branch_1, 384, [3, 1], scope='Conv2d_0b_3X1')
], 3)
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 448, [1, 3], scope='Conv2d_0a_1X1')
branch_2 = slim.conv2d(branch_2, 384, [3, 3],
scope='Conv2d_0b_3X3')
branch_2 = tf.concat([
slim.conv2d(branch_2, 384, [1, 3], scope='Conv2d_0c_1X3'),
slim.conv2d(branch_2, 384, [3, 1], scope='Conv2d_0d_3X1')
], 3)
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3X3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1],
scope='Conv2d_0b_1X1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
return net, end_points
# 实现全局平均池化,softmax,auxiliary logits,并构筑网络的整个部分
def inception_v3(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
prediction_fn=slim.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV3'):
with tf.variable_scope(scope, 'InceptionV3', [inputs, num_classes],
reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = inception_v3_base(inputs, scope=scope)
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='SAME'):
aux_logits = end_points['Mixed_6e']
with tf.variable_scope('AuxLogits'):
aux_logits = slim.avg_pool2d(
aux_logits, [5, 5], stride=3, padding='VALID',
scope='AvgPool_1a_5X5'
)
aux_logits = slim.conv2d(aux_logits, 128, [1, 1],
scope='Conv2d_1b_1X1')
aux_logits = slim.conv2d(
aux_logits, 786, [5, 5],
weights_initializer=trunc_normal(0.01),
padding='VALID', scope='Conv2d_2a_5X5'
)
aux_logits = slim.conv2d(
aux_logits, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, weights_initializer=trunc_normal(0.001),
scope='Conv2d_2b_1X1'
)
if spatial_squeeze:
aux_logits = tf.squeeze(aux_logits, [1, 2],
name='SpatialSqueeze')
end_points['AuxLogits'] = aux_logits
with tf.variable_scope('Logits'):
net = slim.avg_pool2d(net, [8, 8], padding='VALID',
scope='AvgPool_1a_8X8')
net = slim.dropout(net, keep_prob=dropout_keep_prob,
scope='Dropout_1b')
end_points['PreLogits'] = net
logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='Conv2d_1c_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
num_batches = 100
# 进行性能测试
def time_tensorflow_run(session, target, info_string):
num_steps_burn_in = 10
total_duration = 0.0
total_duration_squared = 0.0
for i in range(num_batches + num_steps_burn_in):
start_time = time.time()
_ = session.run(target)
duration = time.time() - start_time
if i >= num_steps_burn_in:
if not i % 10:
print('%s: step %d, duration = %.3f' %
(datetime.now(), i - num_steps_burn_in, duration))
total_duration += duration
total_duration_squared += duration * duration
mn = total_duration / num_batches
vr = total_duration_squared / num_batches - mn * mn
sd = math.sqrt(vr)
print('%s: %s across %d step, %.3f +/- %.3f sec / batch' %
(datetime.now(), info_string, num_batches, mn, sd))
batch_size = 32
height, width = 299, 299
inputs = tf.random_uniform((batch_size, height, width, 3))
with slim.arg_scope(inception_v3_arg_scope()):
logits, end_points = inception_v3(inputs, is_training=False)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
time_tensorflow_run(sess, logits, "Forward")
结果如下: