Pytorch迁移学习

  |   0 评论   |   0 浏览   |   给我丶鼓励

在实践中,很少有人从头开始训练整个卷积网络(使用随机初始化),因为拥有足够大小的数据集相对很少。取而代之的是,通常在非常大的数据集上对 ConvNet 进行预训练(例如 ImageNet,其中包含 120 万个图像,具有 1000 个类别),然后将 ConvNet 用作初始化或固定特征提取器以完成感兴趣的任务。

这两个主要的转移学习方案如下所示:

  • 微调 convnet:我们不是使用随机初始化,而是使用预训练的网络初始化网络,就像在 imagenet 1000 数据集上训练的网络一样。其余的培训照常进行。
  • ConvNet 作为固定特征提取器:在这里,我们将冻结除最终完全连接层之外的所有网络的权重。最后一个完全连接的层将替换为具有随机权重的新层,并且仅训练该层。
# License: BSD
# Author: Sasank Chilamkurthy

from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy

plt.ion()   # interactive mode

载入资料

我们将使用 torchvision 和 torch.utils.data 包来加载数据。

我们今天要解决的问题是训练一个模型来对蚂蚁蜜蜂进行分类 。我们为蚂蚁和蜜蜂提供了大约 120 张训练图像。每个类别有 75 个验证图像。通常,如果从头开始训练的话,这是一个很小的数据集。由于我们正在使用迁移学习,因此我们应该能够很好地概括。

该数据集是 imagenet 的很小一部分。

注意

此处下载数据 并将其解压缩到当前目录。

# Data augmentation and normalization for training
# Just normalization for validation
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

data_dir = 'data/hymenoptera_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                             shuffle=True, num_workers=4)
              for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

可视化一些图像

让我们可视化一些训练图像以了解数据扩充。

def imshow(inp, title=None):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    inp = np.clip(inp, 0, 1)
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)  # pause a bit so that plots are updated


# Get a batch of training data
inputs, classes = next(iter(dataloaders['train']))

# Make a grid from batch
out = torchvision.utils.make_grid(inputs)

imshow(out, title=[class_names[x] for x in classes])

训练模型

现在,让我们编写一个通用函数来训练模型。在这里,我们将说明:

  • 安排学习率
  • 保存最佳模型

在下面,parameter scheduler 是的 LR 调度程序对象 torch.optim.lr_scheduler

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # Set model to training mode
            else:
                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                # track history if only in train
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
            if phase == 'train':
                scheduler.step()

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model

可视化模型预测

通用功能,显示一些图像的预测

def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()

    with torch.no_grad():
        for i, (inputs, labels) in enumerate(dataloaders['val']):
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)

            for j in range(inputs.size()[0]):
                images_so_far += 1
                ax = plt.subplot(num_images//2, 2, images_so_far)
                ax.axis('off')
                ax.set_title('predicted: {}'.format(class_names[preds[j]]))
                imshow(inputs.cpu().data[j])

                if images_so_far == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)

微调 convnet

加载预训练的模型并重置最终的完全连接层。

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
# Here the size of each output sample is set to 2.
# Alternatively, it can be generalized to nn.Linear(num_ftrs, len(class_names)).
model_ft.fc = nn.Linear(num_ftrs, 2)

model_ft = model_ft.to(device)

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

训练和评估

在 CPU 上大约需要 15-25 分钟。但是在 GPU 上,此过程不到一分钟。

model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
                       num_epochs=25)

输出:

Epoch 0/24
----------
train Loss: 0.6582 Acc: 0.6557
val Loss: 0.3519 Acc: 0.8758

Epoch 1/24
----------
train Loss: 0.5232 Acc: 0.7910
val Loss: 0.2772 Acc: 0.8693

Epoch 2/24
----------
train Loss: 0.3709 Acc: 0.8443
val Loss: 0.1982 Acc: 0.9085

visualize_model(model_ft)

ConvNet 作为固定特征提取器

在这里,我们需要冻结除最后一层之外的所有网络。我们需要设置冻结参数,以免在中计算梯度。requires_grad == Falsebackward()

model_conv = torchvision.models.resnet18(pretrained=True)
for param in model_conv.parameters():
    param.requires_grad = False

# Parameters of newly constructed modules have requires_grad=True by default
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)

model_conv = model_conv.to(device)

criterion = nn.CrossEntropyLoss()

# Observe that only parameters of final layer are being optimized as
# opposed to before.
optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)

训练和评估

与以前的方案相比,在 CPU 上将花费大约一半的时间。这是可以预期的,因为对于大多数网络而言,不需要计算梯度。但是,确实需要计算正向。

model_conv = train_model(model_conv, criterion, optimizer_conv,
                         exp_lr_scheduler, num_epochs=25)

输出:

Epoch 0/24
----------
train Loss: 0.6355 Acc: 0.6639
val Loss: 0.2097 Acc: 0.9085

Epoch 1/24
----------
train Loss: 0.4946 Acc: 0.7910
val Loss: 0.1839 Acc: 0.9412

Epoch 2/24
----------
train Loss: 0.5700 Acc: 0.7500
val Loss: 0.1874 Acc: 0.9346
visualize_model(model_conv)

plt.ioff()
plt.show()


标题:Pytorch迁移学习
作者:给我丶鼓励
地址:https://blog.doiduoyi.com/articles/1591263934766.html

评论

发表评论