pytorch vision 学习

第一次学习pytorch 看完了几个视频 稍微记录一下 免完全忘记
学习了PyTorch的安装和配置
Dataset类
TensorBoard可视化的使用
常见的transforms
DataLoader的使用
神经网络的基本骨架
损失函数与反向传播
优化器
完整的模型训练套路
利用GPU训练
下边是个gpu训练的例子及使用

gpu训练代码

#!/usr/bin/python3.6
# -*- coding: utf-8 -*-
# @Time    : 2021/12/20 5:38 下午
# @Author  : 李萌周
# @Email   : @qq.com
# @File    : train_gpu_1.py
# @Software: PyCharm
# @remarks : 无
import torch.optim
import torchvision
#准备数据集
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time

# 定义训练的设备
device = torch.device("cpu")
train_data = torchvision.datasets.CIFAR10(root="../data",train=True,transform=torchvision.transforms.ToTensor(),download=True)


test_data = torchvision.datasets.CIFAR10(root="../data",train=False,transform=torchvision.transforms.ToTensor(),download=True)

# 长度
train_data_size = len(test_data)

test_data_size = len(test_data)

# 如果train_data_size=10，训练数据集长度为10
print("训练数据集长度：{}".format(train_data_size))
print("测试数据集长度：{}".format(test_data_size))

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

#创建网络模型
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__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):
        x = self.model(x)
        return x

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

#损失函数 cuda
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
# 训练轮数
epoch = 20

#添加tensorboard
writer = SummaryWriter("../logs_train")
start_time = time.time()
for i in range(epoch):
    print("------------第{}轮训练开始了------------".format(i+1))
    #训练步骤开始
    for data in train_dataloader:
        imgs,targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        # if torch.cuda.is_available():
        #     imgs = imgs.cuda()
        #     targets = targets.cuda()
        outputs = tudui(imgs)
        loss = loss_fn(outputs,targets)

        #优化器调优
        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
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            # 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).sum()
            total_accuracy = total_accuracy + accuracy
    print("整体数据集上的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_train_step)
    writer.add_scalar("test_accuracy", total_accuracy / test_data_size, total_train_step)
    total_train_step = total_train_step + 1

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

利用google.colab训练的 下载模型 本级测试

下边是测试代码

#!/usr/bin/python3.6
# -*- coding: utf-8 -*-
# @Time    : 2021/12/20 6:40 下午
# @Author  : 李萌周
# @Email   : @qq.com
# @File    : test.py
# @Software: PyCharm
# @remarks : 无
import torch
import torchvision
from PIL import Image
from torch import nn

image_path = "../imgs/img_5.png"
image = Image.open(image_path)

print(image)
image = image.convert('RGB')
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),
                                      torchvision.transforms.ToTensor()])
image = transform(image)
print(image)


class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__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):
        x = self.model(x)
        return x
model = torch.load("tudui_49.pth",map_location=torch.device('cpu'))
print(model)
image = torch.reshape(image,(1,3,32,32))
model.eval()
with torch.no_grad():
    output = model(image)
print(output)

print(output.argmax(1))

训练轮数
epoch = 20。正确率就是0.64xxxxxxx了，
再训练epoch = 50。正确率还是0.64xxxx。。。。
没有什么提升了。
b站视频链接https://www.bilibili.com/video/BV1hE411t7RN?p=32