ResNet50结构图及其keras实现

目录

ResNet50完整结构图

 完整Keras代码

---

 

ResNet50完整结构图

 

 完整Keras代码

     模型部分源码来自：https://blog.csdn.net/wang1127248268/article/details/77258055

     将想要进行训练的图片放在对应文件夹中即可进行训练：

    例如    ./data/train/cat                             其中cat、dog为需要网络分辨的类别，存储在不同文件夹中flow_from_directory

               ./data/train/dog                            会自动对图片进行标记，有几个类别就建立几个文件夹。

               ./data/validation/cat                     train文件夹下的图片用于训练，validation文件夹下的图片用于验证准确性，关于

               ./data/validation/dog                  

               ImageDataGenerator的详细内容可参考：https://blog.csdn.net/caanyee/article/details/52502759 或

                                                                                 https://keras-cn.readthedocs.io/en/latest/

# coding=utf-8
from keras.models import Model
from keras.layers import Input, Dense, BatchNormalization, Conv2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D
from keras.layers import add, Flatten, Activation
from keras.optimizers import SGD
from keras.preprocessing.image import ImageDataGenerator
import numpy as np
from keras.callbacks import TensorBoard
from keras.utils import plot_model

seed = 7
np.random.seed(seed)


def Conv2d_BN(x, nb_filter, kernel_size, strides=(1, 1), padding='same', name=None):
	if name is not None:
		bn_name = name + '_bn'
		conv_name = name + '_conv'
	else:
		bn_name = None
		conv_name = None

	x = Conv2D(nb_filter, kernel_size, padding=padding, strides=strides, name=conv_name)(x)
	x = BatchNormalization(axis=3, name=bn_name)(x)
	x = Activation('relu')(x)
	return x


def Conv_Block(inpt, nb_filter, kernel_size, strides=(1, 1), with_conv_shortcut=False):
	x = Conv2d_BN(inpt, nb_filter=nb_filter[0], kernel_size=(1, 1), strides=strides, padding='same')
	x = Conv2d_BN(x, nb_filter=nb_filter[1], kernel_size=(3, 3), padding='same')
	x = Conv2d_BN(x, nb_filter=nb_filter[2], kernel_size=(1, 1), padding='same')
	if with_conv_shortcut:
		shortcut = Conv2d_BN(inpt, nb_filter=nb_filter[2], strides=strides, kernel_size=kernel_size)
		x = add([x, shortcut])
		return x
	else:
		x = add([x, inpt])
		return x


def creatcnn():
	inpt = Input(shape=(224, 224, 3))
	x = ZeroPadding2D((3, 3))(inpt)
	x = Conv2d_BN(x, nb_filter=64, kernel_size=(7, 7), strides=(2, 2), padding='valid')
	x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='same')(x)

	x = Conv_Block(x, nb_filter=[64, 64, 256], kernel_size=(3, 3), strides=(1, 1), with_conv_shortcut=True)
	x = Conv_Block(x, nb_filter=[64, 64, 256], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[64, 64, 256], kernel_size=(3, 3))

	x = Conv_Block(x, nb_filter=[128, 128, 512], kernel_size=(3, 3), strides=(2, 2), with_conv_shortcut=True)
	x = Conv_Block(x, nb_filter=[128, 128, 512], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[128, 128, 512], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[128, 128, 512], kernel_size=(3, 3))

	x = Conv_Block(x, nb_filter=[256, 256, 1024], kernel_size=(3, 3), strides=(2, 2), with_conv_shortcut=True)
	x = Conv_Block(x, nb_filter=[256, 256, 1024], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[256, 256, 1024], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[256, 256, 1024], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[256, 256, 1024], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[256, 256, 1024], kernel_size=(3, 3))

	x = Conv_Block(x, nb_filter=[512, 512, 2048], kernel_size=(3, 3), strides=(2, 2), with_conv_shortcut=True)
	x = Conv_Block(x, nb_filter=[512, 512, 2048], kernel_size=(3, 3))
	x = Conv_Block(x, nb_filter=[512, 512, 2048], kernel_size=(3, 3))
	x = AveragePooling2D(pool_size=(7, 7))(x)
	x = Flatten()(x)
	x = Dense(2, activation='softmax')(x)

	model = Model(inputs=inpt, outputs=x)
	return model


if __name__ == "__main__":
	sgd = SGD(decay=0.0001, momentum=0.9)
	model = creatcnn()
	plot_model(model, to_file='ResNet50_model.png', show_shapes=True) # 保存模型结构图
	model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

	train_datagen = ImageDataGenerator(
		shear_range=0.2,
		zoom_range=0.2,
		horizontal_flip=True)

	test_datagen = ImageDataGenerator()

	train_generator = train_datagen.flow_from_directory(
		'data/train',
		target_size=(224, 224),
		batch_size=10,
		class_mode='categorical')

	validation_generator = test_datagen.flow_from_directory(
		'data/validation',
		target_size=(224, 224),
		batch_size=10,
		class_mode='categorical')

	model.fit_generator(
		train_generator,
		steps_per_epoch=300,
		epochs=1,
		validation_data=validation_generator,
		validation_steps=24,
		verbose=1)
	model.save_weights('ResNet_weight.h5')