小土堆深度学习笔记

pytorch安装，请查看上篇博客。

读取图片操作

from PIL import Image

img_path = "D:\\pythonProject\\learn_pytorch\\dataset\\train\\ants\\0013035.jpg"
img = Image.open(img_path)
img.show()

dir_path="dataset/train/ants"
import os
img_path_list = os.listdir(dir_path)
img_path_list[0]
Out[16]: '0013035.jpg'

from torch.utils.data import Dataset
from PIL import Image
import os

class MyData(Dataset):
    def __init__(self, root_dir, label_dir):
        self.root_dir = root_dir
        self.label_dir = label_dir
        self.path = os.path.join(self.root_dir, self.label_dir)
        self.img_path_list = os.listdir(self.path)

    def __getitem__(self, idx):
        img_name = self.img_path_list[idx]
        img_item_path = os.path.join(self.root_dir, self.label_dir, img_name)
        img = Image.open(img_item_path)
        label = self.label_dir
        return img, label

    def __len__(self):
        return len(self.img_path_list)

root_dir = "dataset/train"
ants_label_dir = "ants"
ants_dataset = MyData(root_dir, ants_label_dir)

TensorBoard的使用

from torch.utils.tensorboard import SummaryWriter

writer = SummaryWriter("logs")

for i in range(100):
    writer.add_scalar("y=x", 2 * i, i)

writer.close()

在logs文件夹中会出现相关的事件，如下图。

在控制台中输入命令tensorboard --logdir=logs即可出现一个网址，对拟合过程进行一个可视化。

import numpy as np
from torch.utils.tensorboard import SummaryWriter
from PIL import Image

writer = SummaryWriter("logs")
image_path = "dataset/train/ants_image/0013035.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape) # 证明是3通道在后，因此add_image方法需要加上dataformats="HWC"参数。

# add_image这个方法的第二个参数既可以是numpy类型也可以是tensor类型的。
writer.add_image("test", img_array, 1, dataformats="HWC")

writer.close()

Transforms的使用

from torchvision import transforms
from PIL import Image
from torch.utils.tensorboard import SummaryWriter

img_path = "dataset/train/bees_image/16838648_415acd9e3f.jpg"
img_PIL = Image.open(img_path)

writer = SummaryWriter("logs")

# 1、ToTensor该如何使用？
tool = transforms.ToTensor()
img_tensor = tool(img_PIL)

writer.add_image("Tensor_img", img_tensor, 1)

writer.close()

from torchvision import transforms
from PIL import Image
from torch.utils.tensorboard import SummaryWriter

img_path = "dataset/train/bees_image/16838648_415acd9e3f.jpg"
img_PIL = Image.open(img_path)

writer = SummaryWriter("logs")

# 1、ToTensor该如何使用？
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img_PIL)
writer.add_image("Tensor_img", img_tensor)

# Normalize
trans_norm = transforms.Normalize([8, 3, 6], [5, 2, 7])
img_norm = trans_norm(img_tensor)
writer.add_image("Normal_img", img_norm, 2)

# Resize
trans_resize = transforms.Resize((512, 512))
img_resize = trans_resize(img_PIL)
img_resize = trans_totensor(img_resize)
writer.add_image("Resize_img", img_resize, 0)

# Resize2
trans_resize2 = transforms.Resize(512)
trans_compose = transforms.Compose([trans_resize2, trans_totensor])
img_resize2 = trans_compose(img_PIL)
writer.add_image("Resize_img", img_resize2, 1)

# 随即裁剪
trans_randomcrop = transforms.RandomCrop(256)
trans_compose_2 = transforms.Compose([trans_randomcrop, trans_totensor])
for i in range(10):
    img_crop_2 = trans_compose_2(img_PIL)
    writer.add_image("RandomCrop_img", img_crop_2, i)

writer.close()

torchvision中数据集的使用

import torchvision
from torch.utils.tensorboard import SummaryWriter

transforms_compose = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])

train_set = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=transforms_compose, download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=transforms_compose, download=True)

print(test_set[0])
# print(test_set.classes)
#
# img, target = test_set[0]
# print(img)
# print(target)
# print(test_set.classes[target])
# img.show()

writer = SummaryWriter("logs")

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

writer.close()

DataLoader的使用

DataLoader与Dataset的关系

DataLoader是数据加载器，Dataset是数据集。DataLoader设置参数去读取数据，其中，参数表明读那个数据集，每次读多少等。

import torchvision

#准备测试的数据
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

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

writer = SummaryWriter("dataloader")

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

writer.close()

nn.Module神经网络基本骨架

import torch
from torch import nn

class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__init__()

    # Module类里的__call__应该自动调用了forward，你在这里是看不到的
    def forward(self, input):
        output = input + 1
        return output

tudui = Tudui()
x = torch.tensor(1.0)
output = tudui(x)
print(output)

输出：tensor(2.)

卷积操作

import torch
import torch.nn.functional as F

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]])

kernel = torch.tensor([[1, 2, 1],
                       [0, 1, 0],
                       [2, 1, 0]])

input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))

output = F.conv2d(input, kernel, stride=1)
print(output)

输出：tensor([[[[10, 12, 12],
[18, 16, 16],
[13, 9, 3]]]])

神经网络 卷积层

channel的大小和卷积核个数有关，和其尺寸没有关系

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

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

class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__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

tudui = Tudui()

writer = SummaryWriter("dataloader")
step = 0
for data in dataloader:
    imgs, targets = data
    output = tudui(imgs)
    print(imgs.shape)
    print(output.shape)
    writer.add_images("input", imgs, step)
    output = torch.reshape(output, (-1, 3, 30, 30))
    writer.add_images("output", output, step)
    step = step + 1

writer.close()

神经网络 非线性激活

谈谈神经网络中的非线性激活函数——ReLu函数 (zhihu.com)

激活函数是指在多层神经网络中，上层神经元的输出和下层神经元的输入存在一个函数关系，这个函数就是激活函数。

引入非线性激活函数的目的是提高神经网络的非线性拟合能力，增强模型的表达能力。

神经网络 线性层

# 神经网络 线性层
import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoader

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

class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.linear1 = Linear(196608, 10)

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

tudui = Tudui()

for data in dataloader:
    imgs, targets = data
    print(imgs.shape)
    output = torch.flatten(imgs)
    print(output.shape)
    output = tudui(output)
    print(output.shape)

神经网络 搭建小实战

# 搭建网络模型
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter


class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        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.model1(x)
        return x

tudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)

writer = SummaryWriter("logs_seq")
writer.add_graph(tudui, input)
writer.close()

总结

import time

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

# 准备数据集
from torch import nn
from torch.utils.data import DataLoader

start_time = time.time()
train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)

# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 格式化字符串的用法
print("训练数据集的长度{}".format(train_data_size))
print("测试数据集的长度{}".format(test_data_size))

# 利用DataLoader来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

import torch
from torch import nn

# 搭建神经网络
class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.model= nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64*4*4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        return self.model(x)

if __name__ == '__main__':
    tudui = Tudui()
    input = torch.ones((64, 3, 32, 32))
    output = tudui(input)
    print(output.shape)

# 创建网络模型
tudui = Tudui()
if torch.cuda.is_available():
    tudui = tudui.cuda()

# 损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()

# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(), lr = learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10

# 添加tensorboard
writer = SummaryWriter("P28_logs_train")

for i in range(epoch):
    print("-----第{}轮训练开始-----".format(i + 1))

    # 训练步骤开始
    tudui.train()
    for data in train_dataloader:
        imgs, targets = data
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)

        # 优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time - start_time)
            print("训练次数：{}， Loss：{}".format(total_train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    tudui.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            if torch.cuda.is_available():
                imgs = imgs.cuda()
                targets = targets.cuda()
            outputs = tudui(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).max()
            total_accuracy = total_accuracy + accuracy
    print("整体测试集上的Loss:{}".format(total_test_loss))
    print("整体测试集上的正确率:{}".format(total_accuracy/test_data_size))
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
    total_test_step = total_test_step + 1

    torch.save(tudui, "tudui_{}.pth".format(i))
    print("模型已保存")

writer.close()