python神经网络Inception ResnetV2模型复现详解
时间：2022-10-19 10:50:23 | 栏目：Python代码 | 点击：次
什么是Inception ResnetV2
Inception ResnetV2是Inception ResnetV1的一个加强版，两者的结构差距不大，如果大家想了解Inception ResnetV1可以看一下我的另一个blog。facenet的神经网络结构就是Inception ResnetV1。
Inception-ResNetV2的网络结构
Inception-ResNetV2和Inception-ResNetV1采用同一个主干网络。
它的结构很有意思！
如图所示为整个网络的主干结构：
可以看到里面的结构分为几个重要的部分
1、stem
2、Inception-resnet-A
3、Inception-resnet-B
4、Inception-resnet-C
1、Stem的结构：
在Inception-ResNetV2里，它的Input为299x299x3大小，输入后进行：三次卷积 -> 最大池化 -> 两次卷积 -> 最大池化 -> 四个分支 -> 堆叠python实现代码如下：
input_shape = [299,299,3] img_input = Input(shape=input_shape) # Stem block: 299,299,3 -> 35 x 35 x 192 x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid') x = conv2d_bn(x, 32, 3, padding='valid') x = conv2d_bn(x, 64, 3) x = MaxPooling2D(3, strides=2)(x) x = conv2d_bn(x, 80, 1, padding='valid') x = conv2d_bn(x, 192, 3, padding='valid') x = MaxPooling2D(3, strides=2)(x) # Mixed 5b (Inception-A block):35 x 35 x 192 -> 35 x 35 x 320 branch_0 = conv2d_bn(x, 96, 1) branch_1 = conv2d_bn(x, 48, 1) branch_1 = conv2d_bn(branch_1, 64, 5) branch_2 = conv2d_bn(x, 64, 1) branch_2 = conv2d_bn(branch_2, 96, 3) branch_2 = conv2d_bn(branch_2, 96, 3) branch_pool = AveragePooling2D(3, strides=1, padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1) branches = [branch_0, branch_1, branch_2, branch_pool] x = Concatenate(name='mixed_5b')(branches)
2、Inception-resnet-A的结构：
Inception-resnet-A的结构分为四个分支
1、未经处理直接输出
2、经过一次1x1的32通道的卷积处理
3、经过一次1x1的32通道的卷积处理和一次3x3的32通道的卷积处理
4、经过一次1x1的32通道的卷积处理、一次3x3的48通道和一次3x3的64通道卷积处理
234步的结果堆叠后进行一次卷积，并与第一步的结果相加，实质上这是一个残差网络结构。
实现代码如下：
branch_0 = conv2d_bn(x, 32, 1)
branch_1 = conv2d_bn(x, 32, 1)
branch_1 = conv2d_bn(branch_1, 32, 3)
branch_2 = conv2d_bn(x, 32, 1)
branch_2 = conv2d_bn(branch_2, 48, 3)
branch_2 = conv2d_bn(branch_2, 64, 3)
branches = [branch_0, branch_1, branch_2]
block_name = block_type + '_' + str(block_idx)
mixed = Concatenate(name=block_name + '_mixed')(branches)
up = conv2d_bn(mixed,K.int_shape(x)[3],1,activation=None,se_bias=True,name=block_name + '_conv')
x = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,
output_shape=K.int_shape(x)[1:],
arguments={'scale': scale},
name=block_name)([x, up])
if activation is not None:
x = Activation(activation, name=block_name + '_ac')(x)
3、Inception-resnet-B的结构：
Inception-resnet-B的结构分为四个分支
1、未经处理直接输出
2、经过一次1x1的192通道的卷积处理
3、经过一次1x1的128通道的卷积处理、一次1x7的160通道的卷积处理和一次7x1的192通道的卷积处理
23步的结果堆叠后进行一次卷积，并与第一步的结果相加，实质上这是一个残差网络结构。
实现代码如下：
branch_0 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(x, 128, 1)
branch_1 = conv2d_bn(branch_1, 160, [1, 7])
branch_1 = conv2d_bn(branch_1, 192, [7, 1])
branches = [branch_0, branch_1]
block_name = block_type + '_' + str(block_idx)
mixed = Concatenate(name=block_name + '_mixed')(branches)
up = conv2d_bn(mixed,K.int_shape(x)[3],1,activation=None,se_bias=True,name=block_name + '_conv')
x = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,
output_shape=K.int_shape(x)[1:],
arguments={'scale': scale},
name=block_name)([x, up])
if activation is not None:
x = Activation(activation, name=block_name + '_ac')(x)
4、Inception-resnet-C的结构：
Inception-resnet-B的结构分为四个分支
1、未经处理直接输出
2、经过一次1x1的192通道的卷积处理
3、经过一次1x1的192通道的卷积处理、一次1x3的224通道的卷积处理和一次3x1的256通道的卷积处理
23步的结果堆叠后进行一次卷积，并与第一步的结果相加，实质上这是一个残差网络结构。
实现代码如下：
branch_0 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(branch_1, 224, [1, 3])
branch_1 = conv2d_bn(branch_1, 256, [3, 1])
branches = [branch_0, branch_1]
block_name = block_type + '_' + str(block_idx)
mixed = Concatenate(name=block_name + '_mixed')(branches)
up = conv2d_bn(mixed,K.int_shape(x)[3],1,activation=None,se_bias=True,name=block_name + '_conv')
x = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,
output_shape=K.int_shape(x)[1:],
arguments={'scale': scale},
name=block_name)([x, up])
if activation is not None:
x = Activation(activation, name=block_name + '_ac')(x)
全部代码
import warnings
import numpy as np
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Activation,AveragePooling2D,BatchNormalization,Concatenate
from keras.layers import Conv2D,Dense,GlobalAveragePooling2D,GlobalMaxPooling2D,Input,Lambda,MaxPooling2D
from keras.applications.imagenet_utils import decode_predictions
from keras.utils.data_utils import get_file
from keras import backend as K
BASE_WEIGHT_URL = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.7/'
def conv2d_bn(x,filters,kernel_size,strides=1,padding='same',activation='relu',use_bias=False,name=None):
x = Conv2D(filters,
kernel_size,
strides=strides,
padding=padding,
use_bias=use_bias,
name=name)(x)
if not use_bias:
bn_axis = 1 if K.image_data_format() == 'channels_first' else 3
bn_name = None if name is None else name + '_bn'
x = BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(x)
if activation is not None:
ac_name = None if name is None else name + '_ac'
x = Activation(activation, name=ac_name)(x)
return x
def inception_resnet_block(x, scale, block_type, block_idx, activation='relu'):
if block_type == 'block35':
branch_0 = conv2d_bn(x, 32, 1)
branch_1 = conv2d_bn(x, 32, 1)
branch_1 = conv2d_bn(branch_1, 32, 3)
branch_2 = conv2d_bn(x, 32, 1)
branch_2 = conv2d_bn(branch_2, 48, 3)
branch_2 = conv2d_bn(branch_2, 64, 3)
branches = [branch_0, branch_1, branch_2]
elif block_type == 'block17':
branch_0 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(x, 128, 1)
branch_1 = conv2d_bn(branch_1, 160, [1, 7])
branch_1 = conv2d_bn(branch_1, 192, [7, 1])
branches = [branch_0, branch_1]
elif block_type == 'block8':
branch_0 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(branch_1, 224, [1, 3])
branch_1 = conv2d_bn(branch_1, 256, [3, 1])
branches = [branch_0, branch_1]
else:
raise ValueError('Unknown Inception-ResNet block type. '
'Expects "block35", "block17" or "block8", '
'but got: ' + str(block_type))
block_name = block_type + '_' + str(block_idx)
mixed = Concatenate(name=block_name + '_mixed')(branches)
up = conv2d_bn(mixed,K.int_shape(x)[3],1,activation=None,use_bias=True,name=block_name + '_conv')
x = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,
output_shape=K.int_shape(x)[1:],
arguments={'scale': scale},
name=block_name)([x, up])
if activation is not None:
x = Activation(activation, name=block_name + '_ac')(x)
return x
def InceptionResNetV2(input_shape=[299,299,3],
classes=1000):
input_shape = [299,299,3]
img_input = Input(shape=input_shape)
# Stem block: 299,299,3 -> 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block):35 x 35 x 192 -> 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(name='mixed_5b')(branches)
# 10次Inception-ResNet-A block:35 x 35 x 320 -> 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Reduction-A block:35 x 35 x 320 -> 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(name='mixed_6a')(branches)
# 20次Inception-ResNet-B block: 17 x 17 x 1088 -> 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
# Reduction-B block: 17 x 17 x 1088 -> 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(name='mixed_7a')(branches)
# 10次Inception-ResNet-C block: 8 x 8 x 2080 -> 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# 8 x 8 x 2080 -> 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
inputs = img_input
# 创建模型
model = Model(inputs, x, name='inception_resnet_v2')
return model
def preprocess_input(x):
x /= 255.
x -= 0.5
x *= 2.
return x
if __name__ == '__main__':
model = InceptionResNetV2()
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(fname,BASE_WEIGHT_URL + fname,cache_subdir='models',file_hash='e693bd0210a403b3192acc6073ad2e96')
model.load_weights(fname)
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(299, 299))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))