神经网络-完整模型训练

 argmaxs

输入两个数 分别为[[0.1][0.2]]  和[0.3][0.4]

根据热编码的规则为【0,1】

argmaxs(0)表示从上到下取最大的值

argmaxs(1) 表示从左到右取最大的值

假设是argmaxs(1)取的第一个为0.2，在热编码里是属于1的位置，所以取的就是1

图中的preds=[1,1]  

如果我们拿targets进行对比，preds==targets.sum()得出来的就会是[false,true]

这个在分类任务里常用。

模型编写

TensorBoard和网络框架整合出一个基础的模型训练步骤

model1.py

import torch
from torch import nn
# from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear


class Test(nn.Module):
    def __init__(self):
        super(Test, self).__init__()
        self.module1 = 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.module1(x)
        return x
if __name__ == '__main__':
    test = Test()
    input = torch.ones((64,3,32,32))
    output = test(input)
    print(output.shape)

 train1.py

import torchvision.datasets
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from model1 import *

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)
writer = SummaryWriter("logs")

#查看数据长度
train_data_size =len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度为：{}".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)

#创建网络模型
test = Test()

#损失函数
loss_fn = nn.CrossEntropyLoss()
#优化器
#1e-2 = 1*(10)^(-2) = 1/100 = 0.01
learning_rate = 1e-2
optimizer= torch.optim.SGD(test.parameters(),lr=0.01)

#设置训练网络参数
#训练次数
total_train_step = 0
total_test_step = 0
epoch = 10

for i in range(epoch):
    print("-----第{}轮训练开始-----".format(i+1))
    for data in train_dataloader:
        imgs,targets = data
        outputs = test(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:
            print("训练次数：{},Loss{}".format(total_train_step,loss))
            writer.add_scalar("train_loss",loss.item(),total_train_step)
    #测试步骤开始  为了查看模型是否能达到需求
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs,targets = data
            outputs = test(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("整体测试集上的Loss:{}".format(total_test_loss))
    print("整个测试集上的正确率：{}".format(total_accuracy/test_data_size))
    writer.add_scalar("test_loss",total_test_loss,total_test_step)
    total_test_step = total_test_step +1
    #这样可以保存每一次运行的模型结果
    torch.save(test,"test_{}.pth".format(i))
    print("模型已保存")

writer.close()

TensorBoard

在控制台输入：tensorboard --logdir="logs" 点击网址