src/NetWork.py

# -*- coding:utf-8 -*-
# VGG模型代码
import numpy as np
import paddle
# from paddle.nn import Conv2D, MaxPool2D, BatchNorm, Linear
from paddle.nn import Conv2D, MaxPool2D, BatchNorm2D, Linear


# 定义vgg网络
class VGG(paddle.nn.Layer):
    def __init__(self, num_class):
        super(VGG, self).__init__()

        in_channels = [3, 64, 128, 256, 512, 512]
        # 定义第一个卷积块，包含两个卷积 输入通道数是图片通道数即3 输出通道数即out_channels=in_channels[1]=64
        self.conv1_1 = Conv2D(in_channels=in_channels[0], out_channels=in_channels[1], kernel_size=3, padding=1,
                              stride=1)
        self.conv1_2 = Conv2D(in_channels=in_channels[1], out_channels=in_channels[1], kernel_size=3, padding=1,
                              stride=1)
        # 定义第二个卷积块，包含两个卷积 输入通道数是上一个卷积块的输出通道数即64 输出通道数即out_channels=in_channels[2]=128
        self.conv2_1 = Conv2D(in_channels=in_channels[1], out_channels=in_channels[2], kernel_size=3, padding=1,
                              stride=1)
        self.conv2_2 = Conv2D(in_channels=in_channels[2], out_channels=in_channels[2], kernel_size=3, padding=1,
                              stride=1)
        # 定义第三个卷积块，包含三个卷积 输入通道数是上一个卷积块的输出通道数即128 输出通道数即out_channels=in_channels[3]=256
        self.conv3_1 = Conv2D(in_channels=in_channels[2], out_channels=in_channels[3], kernel_size=3, padding=1,
                              stride=1)
        self.conv3_2 = Conv2D(in_channels=in_channels[3], out_channels=in_channels[3], kernel_size=3, padding=1,
                              stride=1)
        self.conv3_3 = Conv2D(in_channels=in_channels[3], out_channels=in_channels[3], kernel_size=3, padding=1,
                              stride=1)
        # 定义第四个卷积块，包含三个卷积 输入通道数是上一个卷积块的输出通道数即256 输出通道数即out_channels=in_channels[4]=512
        self.conv4_1 = Conv2D(in_channels=in_channels[3], out_channels=in_channels[4], kernel_size=3, padding=1,
                              stride=1)
        self.conv4_2 = Conv2D(in_channels=in_channels[4], out_channels=in_channels[4], kernel_size=3, padding=1,
                              stride=1)
        self.conv4_3 = Conv2D(in_channels=in_channels[4], out_channels=in_channels[4], kernel_size=3, padding=1,
                              stride=1)
        # 定义第五个卷积块，包含三个卷积 输入通道数是上一个卷积块的输出通道数即512 输出通道数即out_channels=in_channels[5]=512
        self.conv5_1 = Conv2D(in_channels=in_channels[4], out_channels=in_channels[5], kernel_size=3, padding=1,
                              stride=1)
        self.conv5_2 = Conv2D(in_channels=in_channels[5], out_channels=in_channels[5], kernel_size=3, padding=1,
                              stride=1)
        self.conv5_3 = Conv2D(in_channels=in_channels[5], out_channels=in_channels[5], kernel_size=3, padding=1,
                              stride=1)

        # VGG网络的设计严格使用3*3的卷积层和池化层来提取特征，并在网络的最后面使用三层全连接层，将最后一层全连接层的输出作为分类的预测。
        # 使用Sequential 将全连接层和relu组成一个线性结构（fc + relu）
        # 当输入为224x224时，经过五个卷积块和池化层后，特征维度变为[512x7x7]
        self.fc1 = paddle.nn.Sequential(paddle.nn.Linear(512 * 7 * 7, 4096), paddle.nn.ReLU())

        self.drop1_ratio = 0.5
        self.dropout1 = paddle.nn.Dropout(self.drop1_ratio, mode='upscale_in_train')
        # 使用Sequential 将全连接层和relu组成一个线性结构（fc + relu）
        self.fc2 = paddle.nn.Sequential(paddle.nn.Linear(4096, 4096), paddle.nn.ReLU())

        self.drop2_ratio = 0.5
        self.dropout2 = paddle.nn.Dropout(self.drop2_ratio, mode='upscale_in_train')

        # 全连接层的输出
        # paddle.nn.Linear(in_features, out_features, weight_attr=None, bias_attr=None, name=None)
        # out_features 由输出标签的个数决定 本案例识别的7种表情，对应了3种标签。 因此 out_features = 3
        self.fc3 = paddle.nn.Linear(4096, num_class)

        self.relu = paddle.nn.ReLU()
        self.pool = MaxPool2D(stride=2, kernel_size=2)

    def forward(self, x):
        # 激活函数用relu
        x = self.relu(self.conv1_1(x))
        x = self.relu(self.conv1_2(x))
        x = self.pool(x)

        x = self.relu(self.conv2_1(x))
        x = self.relu(self.conv2_2(x))
        x = self.pool(x)

        x = self.relu(self.conv3_1(x))
        x = self.relu(self.conv3_2(x))
        x = self.relu(self.conv3_3(x))
        x = self.pool(x)

        x = self.relu(self.conv4_1(x))
        x = self.relu(self.conv4_2(x))
        x = self.relu(self.conv4_3(x))
        x = self.pool(x)

        x = self.relu(self.conv5_1(x))
        x = self.relu(self.conv5_2(x))
        x = self.relu(self.conv5_3(x))
        x = self.pool(x)

        x = paddle.flatten(x, 1, -1)
        # 添加dropout抑制过拟合
        x = self.dropout1(self.relu(self.fc1(x)))
        x = self.dropout2(self.relu(self.fc2(x)))
        x = self.fc3(x)
        return x