python神經(jīng)網(wǎng)絡Inception?ResnetV2模型復現(xiàn)詳解
更新時間：2022年05月07日 09:51:16 作者：Bubbliiiing
這篇文章主要為大家介紹了python神經(jīng)網(wǎng)絡Inception?ResnetV2模型復現(xiàn)詳解，有需要的朋友可以借鑒參考下，希望能夠有所幫助，祝大家多多進步，早日升職加薪
什么是Inception ResnetV2
Inception ResnetV2是Inception ResnetV1的一個加強版，兩者的結構差距不大，如果大家想了解Inception ResnetV1可以看一下我的另一個blog。facenet的神經(jīng)網(wǎng)絡結構就是Inception ResnetV1。
神經(jīng)網(wǎng)絡學習——facenet詳解及其keras實現(xiàn)
Inception-ResNetV2的網(wǎng)絡結構
Inception-ResNetV2和Inception-ResNetV1采用同一個主干網(wǎng)絡。
它的結構很有意思！
如圖所示為整個網(wǎng)絡的主干結構：
可以看到里面的結構分為幾個重要的部分
1、stem
2、Inception-resnet-A
3、Inception-resnet-B
4、Inception-resnet-C
1、Stem的結構：
在Inception-ResNetV2里，它的Input為299x299x3大小，輸入后進行：三次卷積 -> 最大池化 -> 兩次卷積 -> 最大池化 -> 四個分支 -> 堆疊python實現(xiàn)代碼如下：
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的結構：
Inception-resnet-A的結構分為四個分支
1、未經(jīng)處理直接輸出
2、經(jīng)過一次1x1的32通道的卷積處理
3、經(jīng)過一次1x1的32通道的卷積處理和一次3x3的32通道的卷積處理
4、經(jīng)過一次1x1的32通道的卷積處理、一次3x3的48通道和一次3x3的64通道卷積處理
234步的結果堆疊后進行一次卷積，并與第一步的結果相加，實質(zhì)上這是一個殘差網(wǎng)絡結構。
實現(xiàn)代碼如下：
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的結構：
Inception-resnet-B的結構分為四個分支
1、未經(jīng)處理直接輸出
2、經(jīng)過一次1x1的192通道的卷積處理
3、經(jīng)過一次1x1的128通道的卷積處理、一次1x7的160通道的卷積處理和一次7x1的192通道的卷積處理
23步的結果堆疊后進行一次卷積，并與第一步的結果相加，實質(zhì)上這是一個殘差網(wǎng)絡結構。
實現(xiàn)代碼如下：
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的結構：
Inception-resnet-B的結構分為四個分支
1、未經(jīng)處理直接輸出
2、經(jīng)過一次1x1的192通道的卷積處理
3、經(jīng)過一次1x1的192通道的卷積處理、一次1x3的224通道的卷積處理和一次3x1的256通道的卷積處理
23步的結果堆疊后進行一次卷積，并與第一步的結果相加，實質(zhì)上這是一個殘差網(wǎng)絡結構。
實現(xiàn)代碼如下：
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)
全部代碼
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
# 創(chuàng)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))
以上就是python神經(jīng)網(wǎng)絡Inception ResnetV2模型復現(xiàn)詳解的詳細內(nèi)容，更多關于Inception ResnetV2模型復現(xiàn)的資料請關注腳本之家其它相關文章！
您可能感興趣的文章:
- Python機器學習利用鳶尾花數(shù)據(jù)繪制ROC和AUC曲線
- 利用Python畫ROC曲線和AUC值計算
- 一文詳解Python灰色預測模型實現(xiàn)示例
- python回歸分析邏輯斯蒂模型之多分類任務詳解
- python深度學習tensorflow訓練好的模型進行圖像分類
- Python實現(xiàn)自動駕駛訓練模型
- python神經(jīng)網(wǎng)絡Keras?GhostNet模型的實現(xiàn)
- python神經(jīng)網(wǎng)絡ShuffleNetV2模型復現(xiàn)詳解
- python神經(jīng)網(wǎng)絡Densenet模型復現(xiàn)詳解
- python神經(jīng)網(wǎng)絡MobileNetV3?small模型的復現(xiàn)詳解
- python神經(jīng)網(wǎng)絡MobileNetV3?large模型的復現(xiàn)詳解
- python模型性能ROC和AUC分析詳解
相關文章
今天小編就為大家分享一篇python3中numpy函數(shù)tile的用法詳解，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧2019-12-12
TensorFlow是一個基于數(shù)據(jù)流編程（dataflow programming）的符號數(shù)學系統(tǒng)，被廣泛應用于各類機器學習，這篇文章主要介紹了tensorflow使用指定gpu的方法,需要的朋友可以參考下2020-02-02
本文主要介紹了Python3中zip()函數(shù)知識點小結，文中通過示例代碼介紹的非常詳細，對大家的學習或者工作具有一定的參考學習價值，需要的朋友們下面隨著小編來一起學習學習吧2023-02-02
python獲得文件創(chuàng)建時間和修改時間的方法
這篇文章主要介紹了python獲得文件創(chuàng)建時間和修改時間的方法,涉及Python針對文件屬性的相關操作技巧,需要的朋友可以參考下2015-06-06
python網(wǎng)絡編程學習筆記(六)：Web客戶端訪問
這篇文章主要介紹了python網(wǎng)絡編程之Web客戶端訪問 ,需要的朋友可以參考下2014-06-06
下面小編就為大家?guī)硪黄狣jango接受前端數(shù)據(jù)的幾種方法總結。小編覺得挺不錯的，現(xiàn)在就分享給大家，也給大家做個參考。一起跟隨小編過來看看吧2016-11-11
pytorch中permute()函數(shù)用法補充說明(矩陣維度變化過程)
這篇文章主要給大家介紹了關于pytorch中permute()函數(shù)用法補充說明的相關資料,本文詳細說明了permute函數(shù)里維度變化的詳細過程,需要的朋友可以參考下2022-04-04
這篇文章主要介紹了python實現(xiàn)百度關鍵詞排名查詢,需要的朋友可以參考下2014-03-03
使用matplotlib庫實現(xiàn)圖形局部數(shù)據(jù)放大顯示的實踐
本文主要介紹了使用matplotlib庫實現(xiàn)圖形局部數(shù)據(jù)放大顯示的實踐，文中通過示例代碼介紹的非常詳細，具有一定的參考價值，感興趣的小伙伴們可以參考一下2022-02-02
這篇文章主要介紹了python使用pandas進行量化回測，文章圍繞pandas進行量化回測的相關資料展開簡單內(nèi)容，文章內(nèi)容可以做一些比較簡單的技術指標測試,需要的朋友可以參考一下2022-03-03