PyTorch核心方法之state_dict()、parameters()参数打印与应用案例

import os 
os.environ['CUDA_VISIBLE_DEVICES'] = '3'
import torch 
import torch.nn.functional as F 
import torch.nn as nn

class LeNet5(nn.Module):
    def __init__(self):
        super(LeNet5, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120) # 这里论文上写的是conv,官方教程用了线性层
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features

net = LeNet5()
print(net)

print(type(net.state_dict()))   # <class 'collections.OrderedDict'>
## 遍历打印
for model_key in net.state_dict():      # 【字典格式】的遍历，获取的是模型的名称
    print(f"{model_key}: {net.state_dict()[model_key].size()}")

params = net.parameters()   
print(type(params))   # <class 'generator'>  生成器  

for param in params:    
    print(param.size())   # 只包含参数信息：具体的参数尺寸

named_params = net.named_parameters()   
print(type(named_params))   # <class 'generator'>  也是一个生成器

for name, param in named_params:
    print(f"{name}: {param.size()}")   # 同时获取网络名称和网络参数

# 示例
for name, param in m.named_parameters():
	param.requires_grad = False
	print(f"Freezing layer {name}")