Spaces:
Paused
Paused
File size: 5,380 Bytes
12645de |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
# -*- 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 |