import torch.nn as nn
from collections import OrderedDict
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.conv1 = nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3)
self.conv2 = nn.Conv2d(64, 64, 3)
self.maxpool1 = nn.MaxPool2d(2, 2)
self.features = nn.Sequential(OrderedDict([
('conv3', nn.Conv2d(64, 128, 3)),
('conv4', nn.Conv2d(128, 128, 3)),
('relu1', nn.ReLU())
]))
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = self.maxpool1(x)
x = self.features(x)
return x
m = Model()
for p in m.parameters():
print(type(p.data), p.size())，今天小编就来说说关于布尔网络的稳定性的定义?下面更多详细答案一起来看看吧!
布尔网络的稳定性的定义
parameters方法- 方法parameters()返回包含模型所有参数的迭代器，包含网络中的所有权值矩阵参数以及偏置参数。
import torch.nn as nn
from collections import OrderedDict
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.conv1 = nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3)
self.conv2 = nn.Conv2d(64, 64, 3)
self.maxpool1 = nn.MaxPool2d(2, 2)
self.features = nn.Sequential(OrderedDict([
('conv3', nn.Conv2d(64, 128, 3)),
('conv4', nn.Conv2d(128, 128, 3)),
('relu1', nn.ReLU())
]))
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = self.maxpool1(x)
x = self.features(x)
return x
m = Model()
for p in m.parameters():
print(type(p.data), p.size())
其输出为：
<class 'torch.Tensor'> torch.Size([64, 3, 3, 3])
<class 'torch.Tensor'> torch.Size([64])
<class 'torch.Tensor'> torch.Size([64, 64, 3, 3])
<class 'torch.Tensor'> torch.Size([64])
<class 'torch.Tensor'> torch.Size([128, 64, 3, 3])
<class 'torch.Tensor'> torch.Size([128])
<class 'torch.Tensor'> torch.Size([128, 128, 3, 3])
<class 'torch.Tensor'> torch.Size([128])
- 一般用来当作optimizer的参数，因为对网络进行训练时，需要将parameters()作为优化器optimizer的参数。
optimizer = torch.optim.SGD(m1.parameters(),
lr = args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
- parameters()返回网络的所有参数，主要是提供给optimizer用的。而要取得网络某一层的参数或者对参数进行一些特殊的处理（如fine-tuning)，则使用named_parameters()更为方便些，named_parameters()返回参数的名称及参数本身，可以按照参数名对一些参数进行处理。
m = Model()
for k, v in m.named_parameters():
print(k, v.size())
输出为：
conv1.weight - torch.Size([64, 3, 3, 3])
conv1.bias - torch.Size([64])
conv2.weight - torch.Size([64, 64, 3, 3])
conv2.bias - torch.Size([64])
features.conv3.weight - torch.Size([128, 64, 3, 3])
features.conv3.bias - torch.Size([128])
features.conv4.weight - torch.Size([128, 128, 3, 3])
features.conv4.bias - torch.Size([128])
再以上面的vgg网络为例：
for k,v in m1.named_parameters():
print(k,v.size())
named_parameters返回的是键值对，k为参数的名称 ，v为参数本身。输出结果为：
vgg.0.weight torch.Size([64, 3, 3, 3])
vgg.0.bias torch.Size([64])
vgg.2.weight torch.Size([64, 64, 3, 3])
vgg.2.bias torch.Size([64])
vgg.5.weight torch.Size([128, 64, 3, 3])
vgg.5.bias torch.Size([128])
vgg.7.weight torch.Size([128, 128, 3, 3])
vgg.7.bias torch.Size([128])
vgg.10.weight torch.Size([256, 128, 3, 3])
vgg.10.bias torch.Size([256])
vgg.12.weight torch.Size([256, 256, 3, 3])
vgg.12.bias torch.Size([256])
vgg.14.weight torch.Size([256, 256, 3, 3])
vgg.14.bias torch.Size([256])
vgg.17.weight torch.Size([512, 256, 3, 3])
vgg.17.bias torch.Size([512])
vgg.19.weight torch.Size([512, 512, 3, 3])
vgg.19.bias torch.Size([512])
vgg.21.weight torch.Size([512, 512, 3, 3])
vgg.21.bias torch.Size([512])
vgg.24.weight torch.Size([512, 512, 3, 3])
vgg.24.bias torch.Size([512])
vgg.26.weight torch.Size([512, 512, 3, 3])
vgg.26.bias torch.Size([512])
vgg.28.weight torch.Size([512, 512, 3, 3])
vgg.28.bias torch.Size([512])
参数名的命名规则：属性名称.参数所属层的编号.weight/bias。 在fine-tuning的时候，给一些特定层的参数赋值是非常方便的，这点在后面在加载预训练模型时会看到。
,
