【Pytorch】完整的模型训练套路(7)

以CIFAR10为例,

model.py

# -*- coding: utf-8 -*-
# 作者:小土堆
# 公众号:土堆碎念
import torch
from torch import nn

# 搭建神经网络
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


if __name__ == '__main__':
    tudui = Tudui()
    # 测试网络结构正确性
    input = torch.ones((64, 3, 32, 32))
    output = tudui(input)
    print(output.shape) # tensor.Size([64, 10])

train.py

# -*- coding: utf-8 -*-
# 作者:小土堆
# 公众号:土堆碎念
import torch
import torchvision
from model import *  # 外部文件
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader

# 准备好的训练数据
train_data = torchvision.datasets.CIFAR10(root="./data", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
# 准备好的测试数据
test_data = torchvision.datasets.CIFAR10(root="./data", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)

# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size=10, 训练数据集的长度为:10
print("训练数据集的长度为:{}".format(train_data_size)) # 训练数据集的长度为:50000
print("测试数据集的长度为:{}".format(test_data_size)) # 测试数据集的长度为:10000


# 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)

# 创建网络模型
tudui = Tudui()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
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("../logs_train")

# 1、for循环里的内容做了10次
for i in range(epoch):
    print("-------第 {} 轮训练开始-------".format(i+1))

    # 2、训练步骤开始
    tudui.train() ###############没有这步也能运行,为什么要有呢?
    # 对特定的层有用, BN,Dropout等
    #

    # 3、从dataloader中取数据
    for data in train_dataloader:
        imgs, targets = data
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)

        # 4、优化器优化模型
        optimizer.zero_grad() # 梯度清零
        loss.backward() # 反向传播
        optimizer.step() # 调用优化器优化参数

        # 5、做了一次训练,训练次数+1,打印相关训练信息
        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            print("训练次数:{}, Loss: {}".format(total_train_step, loss.item()))
            # writer.add_scalar("train_loss", loss.item(), total_train_step)
    
    # 6、测试步骤开始
    # 每训练完一轮,都会在测试数据上跑一遍,用于评估模型怎么样
    tudui.eval() ###############没有这步也能运行
    # 对特定的层有用, BN,Dropout等
    #

    total_test_loss = 0 # 验证集上loss的总和
    total_accuracy = 0 # 整体的正确率
    
    # 没有梯度,不对参数进行调优
    with torch.no_grad():
        # 7、读取测试数据
        for data in test_dataloader:
            imgs, targets = data
            # 传入网络
            outputs = tudui(imgs)
            # 计算loss,注意这里没有反向传播
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            # 计算准确率
            accuracy = (outputs.argmax(1) == targets).sum()
            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

    # 8、每轮训练完成后,保存模型
    torch.save(tudui, "tudui_{}.pth".format(i))
    # 方式二保存
    torch.save(tudui.state_dict(), "tudui_{}.pth".format(i))
    print("模型已保存")

# writer.close()

关于验证部分loss.item()的原因,.item()使得tensor数据转为int数据。

import torch
a = torch.tensor(5)
print(a) # tensor(5), tensor

print(a.item()) # 5, int

求正确率的流程

【Pytorch】完整的模型训练套路(7)_第1张图片

import torch

outputs = torch.tensor([[0.1, 0.2],
                        [0.3, 0.4]])

print(outputs.argmax(1)) # 1是横着看,0是纵着看
# tensor([1, 1])

preds = outputs.argmax(1)

targets = torch.tensor([0, 1])
print(preds==targets)
# tensor([0, 1], dtype=torch.uint8)

print((preds==targets).sum())
# tensor(1)

你可能感兴趣的:(Tensorflow,&,Pytorch)