python神經(jīng)網(wǎng)絡(luò)InceptionV3模型復(fù)現(xiàn)詳解
更新時間：2022年05月06日 15:00:46 作者：Bubbliiiing
這篇文章主要為大家介紹了python神經(jīng)網(wǎng)絡(luò)InceptionV3模型復(fù)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<BR>
學(xué)習(xí)前言
Inception系列的結(jié)構(gòu)和其它的前向神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)不太一樣，每一層的內(nèi)容不是直直向下的，而是分了很多的塊
什么是InceptionV3模型
InceptionV3模型是谷歌Inception系列里面的第三代模型，其模型結(jié)構(gòu)與InceptionV2模型放在了同一篇論文里，其實二者模型結(jié)構(gòu)差距不大，相比于其它神經(jīng)網(wǎng)絡(luò)模型，Inception網(wǎng)絡(luò)最大的特
點在于將神經(jīng)網(wǎng)絡(luò)層與層之間的卷積運算進行了拓展。
如VGG，AlexNet網(wǎng)絡(luò)，它就是一直卷積下來的，一層接著一層；
ResNet則是創(chuàng)新性的引入了殘差網(wǎng)絡(luò)的概念，使得靠前若干層的某一層數(shù)據(jù)輸出直接跳過多層引入到后面數(shù)據(jù)層的輸入部分，后面的特征層的內(nèi)容會有一部分由其前面的某一層線性貢獻(xiàn)。
而Inception網(wǎng)絡(luò)則是采用不同大小的卷積核，使得存在不同大小的感受野，最后實現(xiàn)拼接達(dá)到不同尺度特征的融合。
對于InceptionV3而言，其網(wǎng)絡(luò)中存在著如下的結(jié)構(gòu)。
這個結(jié)構(gòu)使用不同大小的卷積核對輸入進行卷積（這個結(jié)構(gòu)主要在代碼中的block1使用）。
還存在著這樣的結(jié)構(gòu)，利用1x7的卷積和7x1的卷積代替7x7的卷積，這樣可以只使用約（1x7 + 7x1) / (7x7) = 28.6%的計算開銷；
利用1x3的卷積和3x1的卷積代替3x3的卷積，這樣可以只使用約（1x3 + 3x1) / (3x3) = 67%的計算開銷。
下圖利用1x7的卷積和7x1的卷積代替7x7的卷積（這個結(jié)構(gòu)主要在代碼中的block2使用）。
下圖利用1x3的卷積和3x1的卷積代替3x3的卷積（這個結(jié)構(gòu)主要在代碼中的block3使用）。
InceptionV3網(wǎng)絡(luò)部分實現(xiàn)代碼
我一共將InceptionV3劃分為3個block，對應(yīng)著35x35、17x17，8x8維度大小的圖像。每個block中間有許多的part，對應(yīng)著不同的特征層深度，用于特征提取。
#-------------------------------------------------------------#
# InceptionV3的網(wǎng)絡(luò)部分
#-------------------------------------------------------------#
from __future__ import print_function
from __future__ import absolute_import
import warnings
import numpy as np
from keras.models import Model
from keras import layers
from keras.layers import Activation,Dense,Input,BatchNormalization,Conv2D,MaxPooling2D,AveragePooling2D
from keras.layers import GlobalAveragePooling2D,GlobalMaxPooling2D
from keras.engine.topology import get_source_inputs
from keras.utils.layer_utils import convert_all_kernels_in_model
from keras.utils.data_utils import get_file
from keras import backend as K
from keras.applications.imagenet_utils import decode_predictions
from keras.preprocessing import image
def conv2d_bn(x,
filters,
num_row,
num_col,
padding='same',
strides=(1, 1),
name=None):
if name is not None:
bn_name = name + '_bn'
conv_name = name + '_conv'
else:
bn_name = None
conv_name = None
x = Conv2D(
filters, (num_row, num_col),
strides=strides,
padding=padding,
use_bias=False,
name=conv_name)(x)
x = BatchNormalization(scale=False, name=bn_name)(x)
x = Activation('relu', name=name)(x)
return x
def InceptionV3(input_shape=[299,299,3],
classes=1000):
img_input = Input(shape=input_shape)
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
#--------------------------------#
# Block1 35x35
#--------------------------------#
# Block1 part1
# 35 x 35 x 192 -> 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=3,
name='mixed0')
# Block1 part2
# 35 x 35 x 256 -> 35 x 35 x 288
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=3,
name='mixed1')
# Block1 part3
# 35 x 35 x 288 -> 35 x 35 x 288
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=3,
name='mixed2')
#--------------------------------#
# Block2 17x17
#--------------------------------#
# Block2 part1
# 35 x 35 x 288 -> 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch3x3dbl, branch_pool], axis=3, name='mixed3')
# Block2 part2
# 17 x 17 x 768 -> 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=3,
name='mixed4')
# Block2 part3 and part4
# 17 x 17 x 768 -> 17 x 17 x 768 -> 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=3,
name='mixed' + str(5 + i))
# Block2 part5
# 17 x 17 x 768 -> 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=3,
name='mixed7')
#--------------------------------#
# Block3 8x8
#--------------------------------#
# Block3 part1
# 17 x 17 x 768 -> 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3,
strides=(2, 2), padding='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(
branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch7x7x3, branch_pool], axis=3, name='mixed8')
# Block3 part2 part3
# 8 x 8 x 1280 -> 8 x 8 x 2048 -> 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate(
[branch3x3_1, branch3x3_2], axis=3, name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate(
[branch3x3dbl_1, branch3x3dbl_2], axis=3)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=3,
name='mixed' + str(9 + i))
# 平均池化后全連接。
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
inputs = img_input
model = Model(inputs, x, name='inception_v3')
return model
圖片預(yù)測
建立網(wǎng)絡(luò)后，可以用以下的代碼進行預(yù)測。
def preprocess_input(x):
x /= 255.
x -= 0.5
x *= 2.
return x
if __name__ == '__main__':
model = InceptionV3()
model.load_weights("inception_v3_weights_tf_dim_ordering_tf_kernels.h5")
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))
預(yù)測所需的已經(jīng)訓(xùn)練好的InceptionV3模型可以在github下載非常方便。
預(yù)測結(jié)果為：
Predicted: [[('n02504458', 'African_elephant', 0.50874853), ('n01871265', 'tusker', 0.19524273), ('n02504013', 'Indian_elephant', 0.1566972), ('n01917289', 'brain_coral', 0.0008956835), ('n01695060', 'Komodo_dragon', 0.0008260256)]]
這里我推薦一個很不錯的講InceptionV3結(jié)構(gòu)的深度神經(jīng)網(wǎng)絡(luò)Google Inception Net-V3結(jié)構(gòu)圖里面有每一層的結(jié)構(gòu)圖，非常清晰。
以上就是python神經(jīng)網(wǎng)絡(luò)InceptionV3模型復(fù)現(xiàn)詳解的詳細(xì)內(nèi)容，更多關(guān)于python神經(jīng)網(wǎng)絡(luò)InceptionV3模型的資料請關(guān)注腳本之家其它相關(guān)文章！
相關(guān)文章
Python?Pandas?中的數(shù)據(jù)結(jié)構(gòu)詳解
這篇文章主要介紹了Python?Pandas?中的數(shù)據(jù)結(jié)構(gòu)詳解，Pandas有三種數(shù)據(jù)結(jié)構(gòu)Series、DataFrame和Panel，文章圍繞主題展開更多相關(guān)內(nèi)容需要的小伙伴可以參考一下2022-06-06
這篇文章介紹了python自動化破解之破解滑動驗證碼的解決方案，文中通過示例代碼介紹的非常詳細(xì)。對大家的學(xué)習(xí)或工作具有一定的參考借鑒價值，需要的朋友可以參考下2022-07-07
今天小編就為大家分享一篇python腳本后臺執(zhí)行方式，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
今天小編就為大家分享一篇利用python畫出AUC曲線的實例，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2020-02-02
Python對Tornado請求與響應(yīng)的數(shù)據(jù)處理
這篇文章主要介紹了Python對Tornado請求與響應(yīng)的數(shù)據(jù)處理,需要的朋友可以參考下2020-02-02
詳解Python是如何實現(xiàn)issubclass的
這篇文章主要介紹了詳解Python是如何實現(xiàn)issubclass的，文中通過示例代碼介紹的非常詳細(xì)，對大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價值，需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧2019-07-07
使用Python實現(xiàn)發(fā)送郵件的常用方法小結(jié)
在日常工作中,我們可能經(jīng)常會用到發(fā)送郵件,但如果每次都人工來發(fā)送,那豈不是很麻煩,今天我們就來講解下如何通過python語言來優(yōu)雅地發(fā)送郵件2024-04-04
這篇文章主要為大家詳細(xì)介紹了python的函數(shù)形參和返回值，文中示例代碼介紹的非常詳細(xì)，具有一定的參考價值，感興趣的小伙伴們可以參考一下，希望能夠給你帶來幫助2022-03-03
文章介紹了如何使用Pandas工具將兩個關(guān)聯(lián)的Excel文件合并成一個,首先創(chuàng)建兩個Excel文件test1和test2,然后使用Pandas進行合并,最后顯示新創(chuàng)建的Excel文件2025-02-02
在本篇內(nèi)容里小編給各位整理的是一篇關(guān)于python爬蟲中的url下載器用法詳解內(nèi)容，需要的朋友們參考下。2020-11-11