tensorflow：
tensorflow搭建网络有两种方式
方式一：采用函数的方式创建模型，
需要从keras中导入模块layers和Model。
定义函数时形参需要图片的一些属性，采用函数的方式，网络的开始部分一定得是layers.Input(shape=(h,w,c),dtype="")
接下来通过layers.Conv2d等方式创建网络，这种方式需要在网络的最后面加上前一步输出的结果
x = layers.MaxPool2D(pool_size=3, strides=2)(x) ，一定不要忘了
最后一步通过Model模块传入网络的输入，输出即可完成模型的创建
model = models.Model(inputs=input_image, outputs=predict)
或 model = Model(inputs=input_image, outputs=predict)
from tensorflow.keras import layers, models, Model
#需要导入的keras模块
def AlexNet_v1(im_height=224, im_width=224, num_classes=1000):
# tensorflow中的tensor通道排序是NHWC
input_image = layers.Input(shape=(im_height, im_width, 3), dtype="float32") # output(None, 224, 224, 3)
x = layers.ZeroPadding2D(((1, 2), (1, 2)))(input_image) # output(None, 227, 227, 3)
x = layers.Conv2D(48, kernel_size=11, strides=4, activation="relu")(x) # output(None, 55, 55, 48)
x = layers.MaxPool2D(pool_size=3, strides=2)(x) # output(None, 27, 27, 48)
x = layers.Conv2D(128, kernel_size=5, padding="same", activation="relu")(x) # output(None, 27, 27, 128)
x = layers.MaxPool2D(pool_size=3, strides=2)(x) # output(None, 13, 13, 128)
x = layers.Conv2D(192, kernel_size=3, padding="same", activation="relu")(x) # output(None, 13, 13, 192)
x = layers.Conv2D(192, kernel_size=3, padding="same", activation="relu")(x) # output(None, 13, 13, 192)
x = layers.Conv2D(128, kernel_size=3, padding="same", activation="relu")(x) # output(None, 13, 13, 128)
x = layers.MaxPool2D(pool_size=3, strides=2)(x) # output(None, 6, 6, 128)
x = layers.Flatten()(x) # output(None, 6*6*128)
x = layers.Dropout(0.2)(x)
x = layers.Dense(2048, activation="relu")(x) # output(None, 2048)
x = layers.Dropout(0.2)(x)
x = layers.Dense(2048, activation="relu")(x) # output(None, 2048)
x = layers.Dense(num_classes)(x) # output(None, 5)
predict = layers.Softmax()(x)
model = models.Model(inputs=input_image, outputs=predict)
return model方式二：通过继承Model模块
创建模型对象继承Model类，初始化模型对象，初始化父类对象
需要用到keras中的Sequential容器模块
通过创建提取特征层，可以将需要创建的每一步网络都放到Sequential容器中，在继承模块创建模型的方法中每一层网络后面我们不需要加入输入x，只需要在tensorflow前向传播函数call函数中传入输入即可
from tensorflow.keras import layers, Model， Sequential
#需要导入的keras模块
class AlexNet_v2(Model):
def __init__(self, num_classes=1000):
super(AlexNet_v2, self).__init__()
self.features = Sequential([
layers.ZeroPadding2D(((1, 2), (1, 2))), # output(None, 227, 227, 3)
layers.Conv2D(48, kernel_size=11, strides=4, activation="relu"), # output(None, 55, 55, 48)
layers.MaxPool2D(pool_size=3, strides=2), # output(None, 27, 27, 48)
layers.Conv2D(128, kernel_size=5, padding="same", activation="relu"), # output(None, 27, 27, 128)
layers.MaxPool2D(pool_size=3, strides=2), # output(None, 13, 13, 128)
layers.Conv2D(192, kernel_size=3, padding="same", activation="relu"), # output(None, 13, 13, 192)
layers.Conv2D(192, kernel_size=3, padding="same", activation="relu"), # output(None, 13, 13, 192)
layers.Conv2D(128, kernel_size=3, padding="same", activation="relu"), # output(None, 13, 13, 128)
layers.MaxPool2D(pool_size=3, strides=2)]) # output(None, 6, 6, 128)
self.flatten = layers.Flatten()
self.classifier = Sequential([
layers.Dropout(0.2),
layers.Dense(1024, activation="relu"), # output(None, 2048)
layers.Dropout(0.2),
layers.Dense(128, activation="relu"), # output(None, 2048)
layers.Dense(num_classes), # output(None, 5)
layers.Softmax()
])
def call(self, inputs, **kwargs):
x = self.features(inputs)
x = self.flatten(x)
x = self.classifier(x)
return xpytorch：
需要导入两个模块
import torch.nn as nn
import torchpytorch中创建模型方法跟tensorflow中方法二类似，不同在于：
1）tensorflow是通过layers.调用网络方法创建网络层的，而pytorch是通过nn.创建
2）tensorflow创建网络层只需要输出通道值，也就是卷积核的个数，而pytorch输入以及输出通道都需要输入
3）tensorflow中激活函数基层在了网络层中通过activation=“relu”属性调用，而pytorch中需要在网络层后加入nn.Relu(inpalce=True)
4）tensorflow中Flatten层通过layers.调用，pytorch通过torch.调用
5）两者中padding的使用方式也有区别
import torch.nn as nn
import torch
class AlexNet(nn.Module):
def __init__(self, num_classes=1000, init_weights=False):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2), # input[3, 224, 224] output[48, 55, 55]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[48, 27, 27]
nn.Conv2d(48, 128, kernel_size=5, padding=2), # output[128, 27, 27]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 13, 13]
nn.Conv2d(128, 192, kernel_size=3, padding=1), # output[192, 13, 13]
nn.ReLU(inplace=True),
nn.Conv2d(192, 192, kernel_size=3, padding=1), # output[192, 13, 13]
nn.ReLU(inplace=True),
nn.Conv2d(192, 128, kernel_size=3, padding=1), # output[128, 13, 13]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 6, 6]
)
self.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Linear(128 * 6 * 6, 2048),
nn.ReLU(inplace=True),
nn.Dropout(p=0.5),
nn.Linear(2048, 2048),
nn.ReLU(inplace=True),
nn.Linear(2048, num_classes),
)
if init_weights:
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)