Task4Pytorch基础实战

pytorch的实战训练

1.导入包

import os
import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader

2.配置训练环境和超参数

# 配置GPU，这里有两种方式
## 方案一：使用os.environ
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
# 方案二：使用“device”，后续对要使用GPU的变量用.to(device)即可
device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")

## 配置其他超参数，如batch_size, num_workers, learning rate, 以及总的epochs
batch_size = 256
num_workers = 4
lr = 1e-4
epochs = 20

3.数据读取加载

# 首先设置数据变换
from torchvision import transforms

image_size = 28
data_transform = transforms.Compose([
    transforms.ToPILImage(),   # 这一步取决于后续的数据读取方式，如果使用内置数据集则不需要
    transforms.Resize(image_size),
    transforms.ToTensor()
])

## 读取方式一：使用torchvision自带数据集，下载可能需要一段时间
from torchvision import datasets

train_data = datasets.FashionMNIST(root='./', train=True, download=True, transform=data_transform)
test_data = datasets.FashionMNIST(root='./', train=False, download=True, transform=data_transform)

## 读取方式二：读入csv格式的数据，自行构建Dataset类
class FMDataset(Dataset):
    def __init__(self, df, transform=None):
        self.df = df
        self.transform = transform
        self.images = df.iloc[:,1:].values.astype(np.uint8)
        self.labels = df.iloc[:, 0].values
        
    def __len__(self):
        return len(self.images)
    
    def __getitem__(self, idx):
        image = self.images[idx].reshape(28,28,1)
        label = int(self.labels[idx])
        if self.transform is not None:
            image = self.transform(image)
        else:
            image = torch.tensor(image/255., dtype=torch.float)
        label = torch.tensor(label, dtype=torch.long)
        return image, label

train_df = pd.read_csv("./FashionMNIST/fashion-mnist_train.csv")
test_df = pd.read_csv("./FashionMNIST/fashion-mnist_test.csv")
train_data = FMDataset(train_df, data_transform)
test_data = FMDataset(test_df, data_transform)

构建完训练和测试数据集后要定义DataLorder类，一边训练测试时加载数据

train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=num_workers, drop_last=True)
test_loader = DataLoader(test_data, batch_size=batch_size, shuffle=False, num_workers=num_workers)

进行可视化验证读入数据的正确性

import matplotlib.pyplot as plt
image, label = next(iter(train_loader))
print(image.shape, label.shape)
plt.imshow(image[0][0], cmap="gray")

4.模型设计
构建好模型后放到GPU上用于训练

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 32, 5),
            nn.ReLU(),
            nn.MaxPool2d(2, stride=2),
            nn.Dropout(0.3),
            nn.Conv2d(32, 64, 5),
            nn.ReLU(),
            nn.MaxPool2d(2, stride=2),
            nn.Dropout(0.3)
        )
        self.fc = nn.Sequential(
            nn.Linear(64*4*4, 512),
            nn.ReLU(),
            nn.Linear(512, 10)
        )
        
    def forward(self, x):
        x = self.conv(x)
        x = x.view(-1, 64*4*4)
        x = self.fc(x)
        # x = nn.functional.normalize(x)
        return x

model = Net()
model = model.cuda()
# model = nn.DataParallel(model).cuda()   # 多卡训练时的写法，之后的课程中会进一步讲解

5.设置损失函数
使用torch.nn模块自带的CrossEntropy损失
PyTorch会自动把整数型的label转为one-hot型，用于计算CE loss
这里需要确保label是从0开始的，同时模型不加softmax层（使用logits计算）,这也说明了PyTorch训练中各个部分不是独立的，需要通盘考虑

criterion = nn.CrossEntropyLoss()
# criterion = nn.CrossEntropyLoss(weight=[1,1,1,1,3,1,1,1,1,1])

6.设置优化器

optimizer = optim.Adam(model.parameters(), lr=0.001)#这里用Adam优化器

7.训练和测试（验证）
各自封装成函数，方便后续调用
关注两者的主要区别：
模型状态设置
是否需要初始化优化器
是否需要将loss传回到网络
是否需要每步更新optimizer
此外，对于测试或验证过程，可以计算分类准确率

训练函数
def train(epoch):
    model.train()
    train_loss = 0
    for data, label in train_loader:
        data, label = data.cuda(), label.cuda()
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, label)
        loss.backward()
        optimizer.step()
        train_loss += loss.item()*data.size(0)
    train_loss = train_loss/len(train_loader.dataset)
    print('Epoch: {} \tTraining Loss: {:.6f}'.format(epoch, train_loss))

测试函数
def val(epoch):       
    model.eval()
    val_loss = 0
    gt_labels = []
    pred_labels = []
    with torch.no_grad():
        for data, label in test_loader:
            data, label = data.cuda(), label.cuda()
            output = model(data)
            preds = torch.argmax(output, 1)
            gt_labels.append(label.cpu().data.numpy())
            pred_labels.append(preds.cpu().data.numpy())
            loss = criterion(output, label)
            val_loss += loss.item()*data.size(0)
    val_loss = val_loss/len(test_loader.dataset)
    gt_labels, pred_labels = np.concatenate(gt_labels), np.concatenate(pred_labels)
    acc = np.sum(gt_labels==pred_labels)/len(pred_labels)
    print('Epoch: {} \tValidation Loss: {:.6f}, Accuracy: {:6f}'.format(epoch, val_loss, acc))

调用
for epoch in range(1, epochs+1):
    train(epoch)
    val(epoch)

8.模型保存

save_path = "./FahionModel.pkl"
torch.save(model, save_path)