Pytorch Tutorial 学习笔记 （五）模型训练过程

Pytorch Tutorial 学习笔记 （五）模型训练过程

Pytorch官方文档：https://pytorch.org/tutorials/

数据集

以FashionMNIST数据集为例，Pytorch中自带下载链接

import torch
import torchvision
import torchvision.transforms as transforms

# PyTorch TensorBoard 
from torch.utils.tensorboard import SummaryWriter
from datetime import datetime


transform = transforms.Compose(
    [transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))])

# 创建训练集和验证集, 如果目录下没有该数据集就进行下载
training_set = torchvision.datasets.FashionMNIST('./data', train=True, transform=transform, download=True)
validation_set = torchvision.datasets.FashionMNIST('./data', train=False, transform=transform, download=True)

# 创建数据加载，shuffle是进行打乱操作
training_loader = torch.utils.data.DataLoader(training_set, batch_size=4, shuffle=True, num_workers=2)
validation_loader = torch.utils.data.DataLoader(validation_set, batch_size=4, shuffle=False, num_workers=2)

# 数据标签
classes = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
        'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle Boot')

# 看整个数据集被分成几份
print('Training set has {} instances'.format(len(training_set)))
print('Validation set has {} instances'.format(len(validation_set)))

可视化

import matplotlib.pyplot as plt
import numpy as np

# 将加载进来的数据进行显示
def matplotlib_imshow(img, one_channel=False):
    if one_channel:
        img = img.mean(dim=0)
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    if one_channel:
        plt.imshow(npimg, cmap="Greys")
    else:
        plt.imshow(np.transpose(npimg, (1, 2, 0)))

dataiter = iter(training_loader)
images, labels = dataiter.next()

# 创建网格并进行展示，并输出标签
img_grid = torchvision.utils.make_grid(images)
matplotlib_imshow(img_grid, one_channel=True)
print('  '.join(classes[labels[j]] for j in range(4)))

在实际训练模型过程中也并不一定需要这一步，可以检查图片是否被加载进来或者训练结束进行可视化。

训练模型

import torch.nn as nn
import torch.nn.functional as F

# PyTorch 模型是内嵌在 torch.nn.Module中，下面是卷积层，池化层和全连接层，然后是前向传播通道
class GarmentClassifier(nn.Module):
    def __init__(self):
        super(GarmentClassifier, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 4 * 4, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 4 * 4)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


model = GarmentClassifier()

损失函数

衡量模型训练好坏

loss_fn = torch.nn.CrossEntropyLoss()

# 示例使用的损失函数是交叉熵损失函数，一次加载四张图片，10个类别进行分类
# Represents the model's confidence in each of the 10 classes for a given input
dummy_outputs = torch.rand(4, 10)
# 代表正确类别
dummy_labels = torch.tensor([1, 5, 3, 7])

print(dummy_outputs)
print(dummy_labels)
# 计算交叉熵，也可使用其他损失函数
loss = loss_fn(dummy_outputs, dummy_labels)
print('Total loss for this batch: {}'.format(loss.item()))

优化器

# 优化器是torch.optim...自带的，SGD是随机梯度下降
optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

定义训练过程

def train_one_epoch(epoch_index, tb_writer):
    running_loss = 0.
    last_loss = 0.

    # 加载数据
    for i, data in enumerate(training_loader):
        # 需要图片数据和标签信息
        inputs, labels = data

        # 每一次优化结束进行梯度归零，详情见笔记三
        optimizer.zero_grad()

        # 预测输出
        outputs = model(inputs)

        # 计算损失，梯度回传
        loss = loss_fn(outputs, labels)
        loss.backward()

        # 更新权重
        optimizer.step()

        # 收集训练相关信息
        running_loss += loss.item()
        if i % 1000 == 999:
            last_loss = running_loss / 1000 # loss per batch
            print('  batch {} loss: {}'.format(i + 1, last_loss))
            tb_x = epoch_index * len(training_loader) + i + 1
            tb_writer.add_scalar('Loss/train', last_loss, tb_x)
            running_loss = 0.

    return last_loss

训练过程以及验证

# 训练分为好几个epoch,同一批次数据进行训练好几次
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
writer = SummaryWriter('runs/fashion_trainer_{}'.format(timestamp))
epoch_number = 0

EPOCHS = 5

best_vloss = 1_000_000.

for epoch in range(EPOCHS):
    print('EPOCH {}:'.format(epoch_number + 1))

    # 进入训练模式，也就是会梯度回传更新模型参数
    model.train(True)
    avg_loss = train_one_epoch(epoch_number, writer)

    # 进入测试模式，检测训练效果，梯度不会回传
    model.train(False)

    running_vloss = 0.0
    for i, vdata in enumerate(validation_loader):
        vinputs, vlabels = vdata
        voutputs = model(vinputs)
        vloss = loss_fn(voutputs, vlabels)
        running_vloss += vloss

    avg_vloss = running_vloss / (i + 1)
    print('LOSS train {} valid {}'.format(avg_loss, avg_vloss))
    
    # 训练和测试的损失进行可视化，见学习笔记四
    writer.add_scalars('Training vs. Validation Loss',
                    { 'Training' : avg_loss, 'Validation' : avg_vloss },
                    epoch_number + 1)
    writer.flush()

    # 记录效果最好的模型
    if avg_vloss < best_vloss:
        best_vloss = avg_vloss
        model_path = 'model_{}_{}'.format(timestamp, epoch_number)
        torch.save(model.state_dict(), model_path)

    epoch_number += 1

保存和加载模型

saved_model = GarmentClassifier()
saved_model.load_state_dict(torch.load(PATH))