Mobile-Net v1 tensorflow 源碼解讀
標籤（空格分隔）： tensorflow 源碼
Mobile-Net v1是Xecption結構的一個應用，其目的是將深度網絡應用在移動端上
"""
該代碼主要關注的是mobilenet_v1_base、mobilenet_v1
"""
# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# =============================================================================
"""MobileNet v1.
MobileNet is a general architecture and can be used for multiple use cases.
Depending on the use case, it can use different input layer size and different
head (for example: embeddings, localization and classification).
As described in https://arxiv.org/abs/1704.04861.
MobileNets: Efficient Convolutional Neural Networks for
Mobile Vision Applications
Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang,
Tobias Weyand, Marco Andreetto, Hartwig Adam
100% Mobilenet V1 (base) with input size 224x224:
See mobilenet_v1()
Layer params macs
--------------------------------------------------------------------------------
MobilenetV1/Conv2d_0/Conv2D: 864 10,838,016
MobilenetV1/Conv2d_1_depthwise/depthwise: 288 3,612,672
MobilenetV1/Conv2d_1_pointwise/Conv2D: 2,048 25,690,112
MobilenetV1/Conv2d_2_depthwise/depthwise: 576 1,806,336
MobilenetV1/Conv2d_2_pointwise/Conv2D: 8,192 25,690,112
MobilenetV1/Conv2d_3_depthwise/depthwise: 1,152 3,612,672
MobilenetV1/Conv2d_3_pointwise/Conv2D: 16,384 51,380,224
MobilenetV1/Conv2d_4_depthwise/depthwise: 1,152 903,168
MobilenetV1/Conv2d_4_pointwise/Conv2D: 32,768 25,690,112
MobilenetV1/Conv2d_5_depthwise/depthwise: 2,304 1,806,336
MobilenetV1/Conv2d_5_pointwise/Conv2D: 65,536 51,380,224
MobilenetV1/Conv2d_6_depthwise/depthwise: 2,304 451,584
MobilenetV1/Conv2d_6_pointwise/Conv2D: 131,072 25,690,112
MobilenetV1/Conv2d_7_depthwise/depthwise: 4,608 903,168
MobilenetV1/Conv2d_7_pointwise/Conv2D: 262,144 51,380,224
MobilenetV1/Conv2d_8_depthwise/depthwise: 4,608 903,168
MobilenetV1/Conv2d_8_pointwise/Conv2D: 262,144 51,380,224
MobilenetV1/Conv2d_9_depthwise/depthwise: 4,608 903,168
MobilenetV1/Conv2d_9_pointwise/Conv2D: 262,144 51,380,224
MobilenetV1/Conv2d_10_depthwise/depthwise: 4,608 903,168
MobilenetV1/Conv2d_10_pointwise/Conv2D: 262,144 51,380,224
MobilenetV1/Conv2d_11_depthwise/depthwise: 4,608 903,168
MobilenetV1/Conv2d_11_pointwise/Conv2D: 262,144 51,380,224
MobilenetV1/Conv2d_12_depthwise/depthwise: 4,608 225,792
MobilenetV1/Conv2d_12_pointwise/Conv2D: 524,288 25,690,112
MobilenetV1/Conv2d_13_depthwise/depthwise: 9,216 451,584
MobilenetV1/Conv2d_13_pointwise/Conv2D: 1,048,576 51,380,224
--------------------------------------------------------------------------------
Total: 3,185,088 567,716,352
75% Mobilenet V1 (base) with input size 128x128:
See mobilenet_v1_075()
Layer params macs
--------------------------------------------------------------------------------
MobilenetV1/Conv2d_0/Conv2D: 648 2,654,208
MobilenetV1/Conv2d_1_depthwise/depthwise: 216 884,736
MobilenetV1/Conv2d_1_pointwise/Conv2D: 1,152 4,718,592
MobilenetV1/Conv2d_2_depthwise/depthwise: 432 442,368
MobilenetV1/Conv2d_2_pointwise/Conv2D: 4,608 4,718,592
MobilenetV1/Conv2d_3_depthwise/depthwise: 864 884,736
MobilenetV1/Conv2d_3_pointwise/Conv2D: 9,216 9,437,184
MobilenetV1/Conv2d_4_depthwise/depthwise: 864 221,184
MobilenetV1/Conv2d_4_pointwise/Conv2D: 18,432 4,718,592
MobilenetV1/Conv2d_5_depthwise/depthwise: 1,728 442,368
MobilenetV1/Conv2d_5_pointwise/Conv2D: 36,864 9,437,184
MobilenetV1/Conv2d_6_depthwise/depthwise: 1,728 110,592
MobilenetV1/Conv2d_6_pointwise/Conv2D: 73,728 4,718,592
MobilenetV1/Conv2d_7_depthwise/depthwise: 3,456 221,184
MobilenetV1/Conv2d_7_pointwise/Conv2D: 147,456 9,437,184
MobilenetV1/Conv2d_8_depthwise/depthwise: 3,456 221,184
MobilenetV1/Conv2d_8_pointwise/Conv2D: 147,456 9,437,184
MobilenetV1/Conv2d_9_depthwise/depthwise: 3,456 221,184
MobilenetV1/Conv2d_9_pointwise/Conv2D: 147,456 9,437,184
MobilenetV1/Conv2d_10_depthwise/depthwise: 3,456 221,184
MobilenetV1/Conv2d_10_pointwise/Conv2D: 147,456 9,437,184
MobilenetV1/Conv2d_11_depthwise/depthwise: 3,456 221,184
MobilenetV1/Conv2d_11_pointwise/Conv2D: 147,456 9,437,184
MobilenetV1/Conv2d_12_depthwise/depthwise: 3,456 55,296
MobilenetV1/Conv2d_12_pointwise/Conv2D: 294,912 4,718,592
MobilenetV1/Conv2d_13_depthwise/depthwise: 6,912 110,592
MobilenetV1/Conv2d_13_pointwise/Conv2D: 589,824 9,437,184
--------------------------------------------------------------------------------
Total: 1,800,144 106,002,432
"""
# Tensorflow mandates these.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from collections import namedtuple
import functools
import tensorflow as tf
slim = tf.contrib.slim
# Conv and DepthSepConv namedtuple define layers of the MobileNet architecture
# Conv defines 3x3 convolution layers
# DepthSepConv defines 3x3 depthwise convolution followed by 1x1 convolution.
# stride is the stride of the convolution
# depth is the number of channels or filters in a layer
Conv = namedtuple('Conv', ['kernel', 'stride', 'depth'])
DepthSepConv = namedtuple('DepthSepConv', ['kernel', 'stride', 'depth'])
# _CONV_DEFS specifies the MobileNet body
# _CONV_DEFS預定義了Mobile-Net的核心，當然也可以根據自己需求設計網絡
_CONV_DEFS = [
Conv(kernel=[3, 3], stride=2, depth=32),
DepthSepConv(kernel=[3, 3], stride=1, depth=64),
DepthSepConv(kernel=[3, 3], stride=2, depth=128),
DepthSepConv(kernel=[3, 3], stride=1, depth=128),
DepthSepConv(kernel=[3, 3], stride=2, depth=256),
DepthSepConv(kernel=[3, 3], stride=1, depth=256),
DepthSepConv(kernel=[3, 3], stride=2, depth=512),
DepthSepConv(kernel=[3, 3], stride=1, depth=512),
DepthSepConv(kernel=[3, 3], stride=1, depth=512),
DepthSepConv(kernel=[3, 3], stride=1, depth=512),
DepthSepConv(kernel=[3, 3], stride=1, depth=512),
DepthSepConv(kernel=[3, 3], stride=1, depth=512),
DepthSepConv(kernel=[3, 3], stride=2, depth=1024),
DepthSepConv(kernel=[3, 3], stride=1, depth=1024)
]
def _fixed_padding(inputs, kernel_size, rate=1):
"""Pads the input along the spatial dimensions independently of input size.
Pads the input such that if it was used in a convolution with 'VALID' padding,
the output would have the same dimensions as if the unpadded input was used
in a convolution with 'SAME' padding.
Args:
inputs: A tensor of size [batch, height_in, width_in, channels].
kernel_size: The kernel to be used in the conv2d or max_pool2d operation.
rate: An integer, rate for atrous convolution.
Returns:
output: A tensor of size [batch, height_out, width_out, channels] with the
input, either intact (if kernel_size == 1) or padded (if kernel_size > 1).
"""
kernel_size_effective = [kernel_size[0] + (kernel_size[0] - 1) * (rate - 1),
kernel_size[0] + (kernel_size[0] - 1) * (rate - 1)]
pad_total = [kernel_size_effective[0] - 1, kernel_size_effective[1] - 1]
pad_beg = [pad_total[0] // 2, pad_total[1] // 2]
pad_end = [pad_total[0] - pad_beg[0], pad_total[1] - pad_beg[1]]
padded_inputs = tf.pad(inputs, [[0, 0], [pad_beg[0], pad_end[0]],
[pad_beg[1], pad_end[1]], [0, 0]])
return padded_inputs
#該函數將用戶定義的conv_defs或者_CONV_DEFS展開，建立圖模型
def mobilenet_v1_base(inputs,
final_endpoint='Conv2d_13_pointwise',
min_depth=8,
depth_multiplier=1.0,
conv_defs=None,
output_stride=None,
use_explicit_padding=False,
scope=None):
"""Mobilenet v1.
關鍵參數說明：
final_endpoint: 指定函數最後的輸出；
其他的基本上和mobilenet_v1一樣
Constructs a Mobilenet v1 network from inputs to the given final endpoint.
Args:
inputs: a tensor of shape [batch_size, height, width, channels].
final_endpoint: specifies the endpoint to construct the network up to. It
can be one of ['Conv2d_0', 'Conv2d_1_pointwise', 'Conv2d_2_pointwise',
'Conv2d_3_pointwise', 'Conv2d_4_pointwise', 'Conv2d_5'_pointwise,
'Conv2d_6_pointwise', 'Conv2d_7_pointwise', 'Conv2d_8_pointwise',
'Conv2d_9_pointwise', 'Conv2d_10_pointwise', 'Conv2d_11_pointwise',
'Conv2d_12_pointwise', 'Conv2d_13_pointwise'].
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
conv_defs: A list of ConvDef namedtuples specifying the net architecture.
output_stride: An integer that specifies the requested ratio of input to
output spatial resolution. If not None, then we invoke atrous convolution
if necessary to prevent the network from reducing the spatial resolution
of the activation maps. Allowed values are 8 (accurate fully convolutional
mode), 16 (fast fully convolutional mode), 32 (classification mode).
use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
inputs so that the output dimensions are the same as if 'SAME' padding
were used.
scope: Optional variable_scope.
Returns:
tensor_out: output tensor corresponding to the final_endpoint.
end_points: a set of activations for external use, for example summaries or
losses.
Raises:
ValueError: if final_endpoint is not set to one of the predefined values,
or depth_multiplier <= 0, or the target output_stride is not
allowed.
"""
# 指定“瘦身”後的卷積通道數
depth = lambda d: max(int(d * depth_multiplier), min_depth)
end_points = {}
# Used to find thinned depths for each layer.
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
# 如果用戶未定義，則用官方指定的結構
if conv_defs is None:
conv_defs = _CONV_DEFS
if output_stride is not None and output_stride not in [8, 16, 32]:
raise ValueError('Only allowed output_stride values are 8, 16, 32.')
padding = 'SAME'
if use_explicit_padding:
padding = 'VALID'
with tf.variable_scope(scope, 'MobilenetV1', [inputs]):
with slim.arg_scope([slim.conv2d, slim.separable_conv2d], padding=padding):
# The current_stride variable keeps track of the output stride of the
# activations, i.e., the running product of convolution strides up to the
# current network layer. This allows us to invoke atrous convolution
# whenever applying the next convolution would result in the activations
# having output stride larger than the target output_stride.
current_stride = 1
# The atrous convolution rate parameter.
rate = 1 # 空洞卷積的採樣率
net = inputs
for i, conv_def in enumerate(conv_defs): #循環，展開網絡的配置
end_point_base = 'Conv2d_%d' % i
"""
如果當前stride已經滿足用戶指定的輸出stride 則後面的stride強制爲1
但是rate=rate*stride保證感受野；
如果沒有滿足輸出stride, stride和網絡配置一樣，但是layer_rate=1
"""
if output_stride is not None and current_stride == output_stride:
# If we have reached the target output_stride, then we need to employ
# atrous convolution with stride=1 and multiply the atrous rate by the
# current unit's stride for use in subsequent layers.
layer_stride = 1
layer_rate = rate
rate *= conv_def.stride
else:
layer_stride = conv_def.stride
layer_rate = 1
current_stride *= conv_def.stride
if isinstance(conv_def, Conv):
end_point = end_point_base
if use_explicit_padding:
net = _fixed_padding(net, conv_def.kernel)
net = slim.conv2d(net, depth(conv_def.depth), conv_def.kernel,
stride=conv_def.stride,
normalizer_fn=slim.batch_norm,
scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
elif isinstance(conv_def, DepthSepConv):# 通道分離卷積
end_point = end_point_base + '_depthwise'
# By passing filters=None
# separable_conv2d produces only a depthwise convolution layer
if use_explicit_padding:
net = _fixed_padding(net, conv_def.kernel, layer_rate)
net = slim.separable_conv2d(net, None, conv_def.kernel,
depth_multiplier=1,
stride=layer_stride,
rate=layer_rate,
normalizer_fn=slim.batch_norm,
scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
end_point = end_point_base + '_pointwise'
# 空間分離卷積
net = slim.conv2d(net, depth(conv_def.depth), [1, 1],
stride=1,
normalizer_fn=slim.batch_norm,
scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
else:
raise ValueError('Unknown convolution type %s for layer %d'
% (conv_def.ltype, i))
raise ValueError('Unknown final endpoint %s' % final_endpoint)
#用戶直接調用的函數
"""
關鍵參數說明：
min_depth: 一個卷積層中最少有多少個通道數
depth_multiplier: 在Mobile-Net v1中，作者提到給網絡進行“瘦身“
conv_defs: 用戶可以按照_CONV_DEFS的形式自定義網絡
"""
def mobilenet_v1(inputs,
num_classes=1000,
dropout_keep_prob=0.999,
is_training=True,
min_depth=8,
depth_multiplier=1.0,
conv_defs=None,
prediction_fn=tf.contrib.layers.softmax,
spatial_squeeze=True,
reuse=None,
scope='MobilenetV1',
global_pool=False):
"""Mobilenet v1 model for classification.
Args:
inputs: a tensor of shape [batch_size, height, width, channels].
num_classes: number of predicted classes. If 0 or None, the logits layer
is omitted and the input features to the logits layer (before dropout)
are returned instead.
dropout_keep_prob: the percentage of activation values that are retained.
is_training: whether is training or not.
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
conv_defs: A list of ConvDef namedtuples specifying the net architecture.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
global_pool: Optional boolean flag to control the avgpooling before the
logits layer. If false or unset, pooling is done with a fixed window
that reduces default-sized inputs to 1x1, while larger inputs lead to
larger outputs. If true, any input size is pooled down to 1x1.
Returns:
net: a 2D Tensor with the logits (pre-softmax activations) if num_classes
is a non-zero integer, or the non-dropped-out input to the logits layer
if num_classes is 0 or None.
end_points: a dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: Input rank is invalid.
"""
input_shape = inputs.get_shape().as_list()
if len(input_shape) != 4:
raise ValueError('Invalid input tensor rank, expected 4, was: %d' %
len(input_shape))
with tf.variable_scope(scope, 'MobilenetV1', [inputs], reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
# mobilenet_v1_base將conv_defs網絡配置展開
net, end_points = mobilenet_v1_base(inputs, scope=scope,
min_depth=min_depth,
depth_multiplier=depth_multiplier,
conv_defs=conv_defs)
with tf.variable_scope('Logits'):#如果採用Logits表示網絡的任務進行分類
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
end_points['global_pool'] = net# 此時網絡輸出b,1,1,1024
else:
# Pooling with a fixed kernel size.
kernel_size = _reduced_kernel_size_for_small_input(net, [7, 7])
net = slim.avg_pool2d(net, kernel_size, padding='VALID',
scope='AvgPool_1a')
end_points['AvgPool_1a'] = net
if not num_classes:
return net, end_points
# 1 x 1 x 1024
net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='Conv2d_1c_1x1')
if spatial_squeeze: # 壓縮第2，3維度爲1，此時網絡輸出爲 b,num_classes
logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
if prediction_fn:
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
mobilenet_v1.default_image_size = 224
def wrapped_partial(func, *args, **kwargs):
partial_func = functools.partial(func, *args, **kwargs)
functools.update_wrapper(partial_func, func)
return partial_func
mobilenet_v1_075 = wrapped_partial(mobilenet_v1, depth_multiplier=0.75)
mobilenet_v1_050 = wrapped_partial(mobilenet_v1, depth_multiplier=0.50)
mobilenet_v1_025 = wrapped_partial(mobilenet_v1, depth_multiplier=0.25)
def _reduced_kernel_size_for_small_input(input_tensor, kernel_size):
"""Define kernel size which is automatically reduced for small input.
If the shape of the input images is unknown at graph construction time this
function assumes that the input images are large enough.
Args:
input_tensor: input tensor of size [batch_size, height, width, channels].
kernel_size: desired kernel size of length 2: [kernel_height, kernel_width]
Returns:
a tensor with the kernel size.
"""
shape = input_tensor.get_shape().as_list()
if shape[1] is None or shape[2] is None:
kernel_size_out = kernel_size
else:
kernel_size_out = [min(shape[1], kernel_size[0]),
min(shape[2], kernel_size[1])]
return kernel_size_out
def mobilenet_v1_arg_scope(is_training=True,
weight_decay=0.00004,
stddev=0.09,
regularize_depthwise=False):
"""Defines the default MobilenetV1 arg scope.
Args:
is_training: Whether or not we're training the model.
weight_decay: The weight decay to use for regularizing the model.
stddev: The standard deviation of the trunctated normal weight initializer.
regularize_depthwise: Whether or not apply regularization on depthwise.
Returns:
An `arg_scope` to use for the mobilenet v1 model.
"""
batch_norm_params = {
'is_training': is_training,
'center': True,
'scale': True,
'decay': 0.9997,
'epsilon': 0.001,
}
# Set weight_decay for weights in Conv and DepthSepConv layers.
weights_init = tf.truncated_normal_initializer(stddev=stddev)
regularizer = tf.contrib.layers.l2_regularizer(weight_decay)
if regularize_depthwise:
depthwise_regularizer = regularizer
else:
depthwise_regularizer = None
with slim.arg_scope([slim.conv2d, slim.separable_conv2d],
weights_initializer=weights_init,
activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm):
with slim.arg_scope([slim.batch_norm], **batch_norm_params):
with slim.arg_scope([slim.conv2d], weights_regularizer=regularizer):
with slim.arg_scope([slim.separable_conv2d],
weights_regularizer=depthwise_regularizer) as sc:
return sc
