PyTorch入门2

目录

1. torchvision中数据集的使用

2. DataLoader的使用

3. 神经网络的基本骨架——nn.Module的使用

 4. 神经网络

——卷积层

 ——最大池化的使用

——线性层介绍

---

1. torchvision中数据集的使用

下面主要讲解torchvision.dataset以及dataset如何和transforms联合使用。这部分是对PyTorch入门1中内容的一个总结。

import torchvision
from torch.utils.tensorboard import SummaryWriter

dataset_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])
# 下载数据集
train_set = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=dataset_transform, download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=dataset_transform, download=True)

writer = SummaryWriter("P10")
for i in range(10):
    img, target = test_set[i]
    writer.add_image("test_set", img, i)

writer.close()

2. DataLoader的使用

import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor())
test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=True, num_workers=0, drop_last=False)

writer = SummaryWriter("dataloader")
step = 0
for data in test_loader:
    imgs, targets = data
    print(imgs.shape)
    print(targets)
    writer.add_images("test_data", imgs, step)
    step = step + 1

writer.close()

drop_last=False的时候，如果数据量不能被batch_size整除，会保留最后不够batch_size数量的数据：

3. 神经网络的基本骨架——nn.Module的使用

下面是一个简单的使用nn.Module的例子：

import torch
from torch import nn


class Simple_Example(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, input):
        output = input + 1
        return output

simple_example = Simple_Example()
x = torch.tensor(1.0)
output = simple_example(x)
print(output)

 4. 神经网络

——卷积层

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

testset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(testset, batch_size=64)

class NN_conv2d(nn.Module):
    def __init__(self):
        super(NN_conv2d, self).__init__()
        self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=0)

    def forward(self, x):
        x = self.conv1(x)
        return x

nn_conv2d = NN_conv2d()

writer = SummaryWriter("logs")
step = 0
for data in dataloader:
    imgs, targets = data
    output = nn_conv2d(imgs)
    # print(imgs.shape)
    # torch.Size([64, 3, 32, 32])
    writer.add_images("input", imgs, step)
    # print(output.shape)
    # torch.Size([64, 6, 30, 30])
    # output的channel是6层，无法显示，所以把它的channel reshape成3层的
    output = torch.reshape(output, (-1, 3, 30, 30))
    writer.add_images("output", output, step)
    step = step + 1

writer.close()

 ——最大池化的使用

最大池化的目的：保留输入的特征，同时减少数据量。

import torch
from torch import nn
from torch.nn import MaxPool2d

# MaxPool2d不能处理Long类型的数据，这里输入的数不带小数点则默认为整数类型，所以要设置dtype为float
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)

# -1的地方会自动填充合适的数字
input = torch.reshape(input, (-1, 1, 5, 5))
# print(input.shape)
# 输出结果：torch.Size([1, 1, 5, 5])

class nnmax(nn.Module):
    def __init__(self):
        super(nnmax, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)

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

nn_max = nnmax()
output = nn_max(input)
print(output)
# print(output)的输出如下：
# tensor([[[[2., 3.],
#           [5., 1.]]]])
# 若把ceil_mode设为False，则print(output)的输出如下：
# tensor([[[[2.]]]])

在图像上做最大池化，可视化效果如下：

import torchvision.datasets
from torch import nn
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

testset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(testset, batch_size=64)

class nnmax(nn.Module):
    def __init__(self):
        super(nnmax, self).__init__()
        self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)

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

nn_max = nnmax()

writer = SummaryWriter("logs")
step = 0
for data in dataloader:
    imgs, targets = data
    output = nn_max(imgs)
    writer.add_images("input", imgs, step)
    writer.add_images("output", output, step)
    step = step + 1

writer.close()

——线性层介绍

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

testset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(testset, batch_size=64, drop_last=True)

class linear(nn.Module):
    def __init__(self):
        super(linear, self).__init__()
        self.linear1 = Linear(196608, 10)

    def forward(self, input):
        output = self.linear1(input)
        return output

li = linear()

step = 0
for data in dataloader:
    imgs, tagerts = data
    print(imgs.shape)
    output = torch.reshape(imgs, (1, 1, 1, -1))
    # output = torch.flatten(imgs)
    output = li(output)
    print(output.shape)