Python Pytorch深度学习之神经网络

# -*- coding: utf-8 -*-
"""
Created on Sun Oct 24 15:56:23 2021
@author: Lenovo
"""
# 神经网络
# import torch
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        # 1个输入，6个输出，5*5的卷积
        # 内核
        self.conv1=nn.Conv2d(1,6,5)
        self.conv2=nn.Conv2d(6,16,5)
        # 映射函数：线性——y=Wx+b
        self.fc1=nn.Linear(16*5*5,120)#输入特征值：16*5*5，输出特征值：120
        self.fc2=nn.Linear(120,84)
        self.fc3=nn.Linear(84,10)
    def forward(self,x):
        x=F.max_pool2d(F.relu(self.conv1(x)),(2,2))
        # 如果其尺寸是一个square只能指定一个数字
        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:]
        num_features=1
        for s in size:
            num_features *= s
        return num_features               
net=Net()
print(net)

# 查看模型可训练的参数
params=list(net.parameters())
print(len(params))
print(params[0].size())# conv1 的权重weight

input=torch.randn(1, 1, 32,32)
print(input)
out=net(input)
print(out)

# 调用反向传播
net.zero_grad()
out.backward(torch.randn(1, 10))

如果跟随损失到反向传播路径，可以使用他的.grad_fn属性，将会看到一个计算图

# 在调用loss.backward()时候，整个图都会微分，而且所有的图中的requires_grad=True的张量将会让他们的grad张量累计梯度
#跟随以下步骤反向传播
print(loss.grad_fn)#MSELoss
print(loss.grad_fn.next_functions[0][0])#Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0])#relu

# 调用loss.backward()然后看一下con1的偏置项在反向传播之前和之后的变化
net.zero_grad()
print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)
loss.backward()#反向传播
print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)

# =============================================================================
# # 最简单的更新规则就是随机梯度下降:weight=weight-learning_rate*gradient
# learning_rate=0.01
# for f in net.parameters():
#     f.data.sub_(f.grad.data*learning_rate)#f.data=f.data-learning_rate*gradient
#  =============================================================================

# =============================================================================
# import torch.optim as optim
# optimizer=optim.SGD(net.parameters(), lr=0.01)
# # 在迭代训练过程中
# optimizer.zero_grad()#将现存梯度置零
# output=net(input)
# loss=criterion(output,target)
# loss.backward()#反向传递
# optimizer.step()#更新网络参数
# =============================================================================