标签：data int 基类 stride ace 利用 mode rac super
利用pytorch 定义自己的网络模型时，需要继承toch.nn.Module 基类。
基类中有parameters()、modules()、children()等方法
import torch import torch.nn as nn class myModel(nn.Module): def __init__(self, num_classes): super(myModel, self).__init__() self.conv1 = nn.Sequential(nn.Conv2d(3, 64, kernel_size=3, padding=1), nn.BatchNorm2d(64), nn.ReLU(True)) self.conv2 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=3, padding=1), nn.BatchNorm2d(128), nn.ReLU(True)) self.conv3 = nn.Conv2d(128, 128, kernel_size=3, padding=1) self.avgpool = nn.AvgPool2d(2) self.fc = nn.Linear(5*5*128, num_classes) def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = self.conv3(x) x = self.avgpool(x) x = x.view(x.size(0), -1) x = self.fc(x) return x
看一下parameters方法
mymodel = myModel(100) for m in mymodel.parameters(): print(‘---------------‘) print(m.name, m.shape) >>>--------------- None torch.Size([64, 3, 3, 3]) --------------- None torch.Size([64]) --------------- None torch.Size([64]) --------------- None torch.Size([64]) --------------- None torch.Size([128, 64, 3, 3]) --------------- None torch.Size([128]) --------------- None torch.Size([128]) list(mymodel.parameters()) >>>[Parameter containing: tensor([[[[ 0.1143, 0.1445, 0.0634], [-0.1294, -0.1618, 0.0916], [-0.1492, -0.0222, 0.1498]], [[-0.1576, -0.0599, 0.0668], [ 0.0777, 0.1712, -0.1479], [-0.0921, -0.0166, -0.1750]],
看一下modules()方法
for m in mymodel.modules(): print(‘---------------‘) print(m) --------------- myModel( (conv1): Sequential( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv2): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (avgpool): AvgPool2d(kernel_size=2, stride=2, padding=0) (fc): Linear(in_features=3200, out_features=100, bias=True) ) --------------- Sequential( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) --------------- Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) --------------- BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) --------------- ReLU(inplace=True) --------------- Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) --------------- Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) --------------- BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) --------------- ReLU(inplace=True) --------------- Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) --------------- AvgPool2d(kernel_size=2, stride=2, padding=0) --------------- Linear(in_features=3200, out_features=100, bias=True)
看一下children()方法
for m in mymodel.children(): print(‘---------------‘) print(m) --------------- Sequential( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) --------------- Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) --------------- Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) --------------- AvgPool2d(kernel_size=2, stride=2, padding=0) --------------- Linear(in_features=3200, out_features=100, bias=True)
比较一下chiildren() 方法和 modules() 方法
model.modules()会遍历model中所有的子层，而model.children()仅会遍历当前层，如上所示
所以在进行参数初始化的时候，需要运用self.modules() 【类内初始化】或者model.modules()【类外初始化】，这样可以保证初始化所以的参数
初始化w ： weight.data.具体方式（normal_、fill_(1)、zero_()）
初始化b ： bias.data.具体方式（normal_、fill_(1)、zero_()）
for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2D): m.weight.data.fill_(1) m.bias.data.zero_()
nn.init.kaiming_normal_
def initialize_weights(*models): for model in models: for m in model.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight.data, nonlinearity=‘relu‘) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1.) m.bias.data.fill_(1e-4) elif isinstance(m, nn.Linear): m.weight.data.normal_(0.0, 0.0001) m.bias.data.zero_()
还有一个常用的方法来设置参数是否需要反向传播
model.parameters().requires_grad = False
其他获取模型信息方法
mymodel.fc >>>Linear(in_features=3200, out_features=100, bias=True) mymodel.fc.in_features >>>3200 mymodel.conv3.in_channels >>>128
标签：data int 基类 stride ace 利用 mode rac super
原文地址：https://www.cnblogs.com/learningcaiji/p/13922867.html
