Python 笔记 PyTorch nn_loss_optim && nn_maxpool

#nn_loss_optim#

import torchvision.datasets
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch import nn
import torch
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import tqdm


"""
    损失函数: 1.计算实际输出和目标之间的差距 2.为我们更新输出提供了一定的依据(方向传播), grad
    
    optim 优化器:torch.optim.SGD(, lr)
    lr: 学习速率
"""

dataset = torchvision.datasets.CIFAR10("D:/dev/python/pyWork/Season2/Stage1/data/myimg",
                                       train=False, transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=1)


class Test(nn.Module):

    def __init__(self, *args, **kwargs) -> None:
        super().__init__(*args, **kwargs)
        # 利用Sequential使代码更简洁, 更易管理
        self.module1 = 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.module1(x)
        return x


loss = nn.CrossEntropyLoss()  # 创建损失函数对象
test = Test()
optim = torch.optim.SGD(test.parameters(), lr=0.01)

for epoch in range(20):  # 进行20轮的训练
    running_loss = 0.0
    for data in dataloader:
        imgs, targets = data
        outputs = test(imgs)
        result_loss = loss(outputs, targets)  # 计算损失
        optim.zero_grad()  # 将梯度设置为零
        result_loss.backward()  # 反向传播
        optim.step()  # 调优
        running_loss = running_loss + result_loss
    print(running_loss)

#nn_maxpool#

import torch
import torchvision
from torch import nn
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader

"""
    torch.nn.MaxPool2d(kernel_size, stride, padding, dilation=1, return_indices=False, ceil_mode=False)
    ceil_mode: 向上或向下取整, 默认为False 向下取整
"""

test_set = torchvision.datasets.CIFAR10(root="D:/dev/python/pyWork/Season2/Stage1/data/myimg", train=False,
                                        transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(test_set, batch_size=64)

input = torch.tensor([[1, 2, 0, 3, 1],
                      [0, 1, 2, 3, 1],
                      [1, 2, 1, 0, 0],
                      [5, 2, 3, 1, 1],
                      [2, 1, 0, 1, 1]], dtype=torch.float32)

input = torch.reshape(input, (-1, 1, 5, 5))


class Test(nn.Module):

    def __init__(self, *args, **kwargs) -> None:
        super().__init__(*args, **kwargs)
        self.maxpool1 = MaxPool2d(3, ceil_mode=True)

    def forward(self, input):
        output = self.maxpool1(input)
        return output


test = Test()
output = test(input)

print(output)

for data in dataloader:
    imgs, targets = data
    print(imgs.size)