哔哩大学的PyTorch深度学习快速入门教程(绝对通俗易懂!)【小土堆】
的P24讲讲述了神经网络优化器的使用。
首先优化器的简单例子注释:
for input, target in dataset:
optimizer.zero_grad()
# 接最后一步,到第一步继续循环,需要把上一步的loss。backword求出来的每一个参数对应的梯度清零,以防上一步造成影响
output = model(input)
# 输入经过一个模型得到输出
loss = loss_fn(output, target)
# 输出和真实的target计算出loss,即误差
loss.backward()
# 调用误差的反向传播,得到每个要更新参数得到的梯度
optimizer.step()
# 每个参数根据得到的梯度进行优化,到这步后卷积核中的参数就会有一个调整
对上一讲的网络模型进行梯度优化,代码注释如下:
import torch
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
dataset = torchvision.datasets.CIFAR10("data", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
dataloader = DataLoader(dataset, batch_size=1)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
# self.conv1 = Conv2d(3, 32, 5, padding=2) # 前三个参数见图片,图中是32*32变成32*32,padding的算法为图片
# self.maxpool1 = MaxPool2d(2)
# self.conv2 = Conv2d(3, 32, 5, padding=2)
# self.maxpool2 = MaxPool2d(2)
# self.conv3 = Conv2d(32, 64, 5, padding=2)
# self.maxpool3 = MaxPool2d(2)
# self.flatten = Flatten()
# self.linear1 = Linear(1024, 64)
# self.linear2 = Linear(64, 10)
self.model1 = Sequential(
Conv2d(3, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 64, 5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024, 64),
Linear(64, 10)
)
def forward(self, x):
# x = self.conv1(x)
# x = self.maxpool1(x)
# x = self.conv2(x)
# x = self.maxpool2(x)
# x = self.conv3(x)
# x = self.maxpool3(x)
# x = self.flatten(x)
# self.linear1(x)
# self.linear2(x)
x = self.model1(x)
return x
loss = nn.CrossEntropyLoss()
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters(), lr=0.01)
# 设置优化器
# 再套一个循环,多次学习,循环20次
for epoch in range(20):
running_loss = 0.0
for data in dataloader:
imgs, targets = data
outputs = tudui(imgs)
result_loss = loss(outputs, targets)
# 计算出输出和真实网络的差距
optim.zero_grad()
# 梯度设置为0
result_loss.backward()
optim.step()
running_loss = running_loss + result_loss
# 求整体误差的总和
print(running_loss)
结果为:
每次的结果都优化一下,共20次,代码中有具体注释,可以结合第23讲来看。