快捷導(dǎo)航

python神經(jīng)網(wǎng)絡(luò)ResNet50模型的復(fù)現(xiàn)詳解

更新時間：2022年05月06日 16:03:47 作者：Bubbliiiing

這篇文章主要為大家介紹了python神經(jīng)網(wǎng)絡(luò)ResNet50模型的復(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(jìn)步，早日升職加薪

什么是殘差網(wǎng)絡(luò)

最近看yolo3里面講到了殘差網(wǎng)絡(luò)，對這個網(wǎng)絡(luò)結(jié)構(gòu)很感興趣，于是了解到這個網(wǎng)絡(luò)結(jié)構(gòu)最初的使用是在ResNet網(wǎng)絡(luò)里。

Residual net(殘差網(wǎng)絡(luò))：

將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。

意味著后面的特征層的內(nèi)容會有一部分由其前面的某一層線性貢獻(xiàn)。

其結(jié)構(gòu)如下：

深度殘差網(wǎng)絡(luò)的設(shè)計是為了克服由于網(wǎng)絡(luò)深度加深而產(chǎn)生的學(xué)習(xí)效率變低與準(zhǔn)確率無法有效提升的問題。

什么是ResNet50模型

ResNet50有兩個基本的塊，分別名為Conv Block和Identity Block，其中Conv Block輸入和輸出的維度是不一樣的，所以不能連續(xù)串聯(lián)，它的作用是改變網(wǎng)絡(luò)的維度；

Identity Block輸入維度和輸出維度相同，可以串聯(lián)，用于加深網(wǎng)絡(luò)的。

Conv Block的結(jié)構(gòu)如下：

Identity Block的結(jié)構(gòu)如下：

這兩個都是殘差網(wǎng)絡(luò)結(jié)構(gòu)。

總的網(wǎng)絡(luò)結(jié)構(gòu)如下：

這樣看起來可能比較抽象，還有一副很好的我從網(wǎng)上找的圖，可以拉到最后面去看哈，放前面太占位置了。

ResNet50網(wǎng)絡(luò)部分實現(xiàn)代碼

#-------------------------------------------------------------#
#   ResNet50的網(wǎng)絡(luò)部分
#-------------------------------------------------------------#
from __future__ import print_function
import numpy as np
from keras import layers
from keras.layers import Input
from keras.layers import Dense,Conv2D,MaxPooling2D,ZeroPadding2D,AveragePooling2D
from keras.layers import Activation,BatchNormalization,Flatten
from keras.models import Model
from keras.preprocessing import image
import keras.backend as K
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import preprocess_input
def identity_block(input_tensor, kernel_size, filters, stage, block):
    filters1, filters2, filters3 = filters
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters2, kernel_size,padding='same', name=conv_name_base + '2b')(x)
    x = BatchNormalization(name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(name=bn_name_base + '2c')(x)
    x = layers.add([x, input_tensor])
    x = Activation('relu')(x)
    return x
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):
    filters1, filters2, filters3 = filters
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    x = Conv2D(filters1, (1, 1), strides=strides,
               name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters2, kernel_size, padding='same',
               name=conv_name_base + '2b')(x)
    x = BatchNormalization(name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)
    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(name=bn_name_base + '2c')(x)
    shortcut = Conv2D(filters3, (1, 1), strides=strides,
                      name=conv_name_base + '1')(input_tensor)
    shortcut = BatchNormalization(name=bn_name_base + '1')(shortcut)
    x = layers.add([x, shortcut])
    x = Activation('relu')(x)
    return x
def ResNet50(input_shape=[224,224,3],classes=1000):
    img_input = Input(shape=input_shape)
    x = ZeroPadding2D((3, 3))(img_input)
    x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
    x = BatchNormalization(name='bn_conv1')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((3, 3), strides=(2, 2))(x)
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
    x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
    x = AveragePooling2D((7, 7), name='avg_pool')(x)
    x = Flatten()(x)
    x = Dense(classes, activation='softmax', name='fc1000')(x)
    model = Model(img_input, x, name='resnet50')
    model.load_weights("resnet50_weights_tf_dim_ordering_tf_kernels.h5")
    return model

圖片預(yù)測

建立網(wǎng)絡(luò)后，可以用以下的代碼進(jìn)行預(yù)測。

if __name__ == '__main__':
    model = ResNet50()
    model.summary()
    img_path = 'elephant.jpg'
    img = image.load_img(img_path, target_size=(224, 224))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    x = preprocess_input(x)
    print('Input image shape:', x.shape)
    preds = model.predict(x)
    print('Predicted:', decode_predictions(preds))

預(yù)測所需的已經(jīng)訓(xùn)練好的ResNet50模型可以在https://github.com/fchollet/deep-learning-models/releases下載。非常方便。

預(yù)測結(jié)果為：

Predicted: [[('n01871265', 'tusker', 0.41107917), ('n02504458', 'African_elephant', 0.39015812), ('n02504013', 'Indian_elephant', 0.12260196), ('n03000247', 'chain_mail', 0.023176488), ('n02437312', 'Arabian_camel', 0.020982226)]]

ResNet50模型的完整的結(jié)構(gòu)圖

以上就是python神經(jīng)網(wǎng)絡(luò)ResNet50模型的復(fù)現(xiàn)詳解的詳細(xì)內(nèi)容，更多關(guān)于ResNet50模型復(fù)現(xiàn)的資料請關(guān)注腳本之家其它相關(guān)文章！

您可能感興趣的文章: