基于PyTorch的深度学习入门教程_transfer_learning_tutorial

摘要

"""
迁移学习教程
= = = = = = = = = = = = = = = = = = = = = = = = = =
**作者**:' Sasank Chilamkurthy ' _

在本教程中，您将学习如何使用迁移学习来训练您的网络。您可以通过cs231n notes <https://cs231n.github.io/transfer-learning/>阅读更多关于迁移学习的信息

引用这些笔记

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较少。相反，通常在非常大的数据集(例如ImageNet，它包含120万幅包含1000个类别的图像)上对ConvNet进行预训练，然后使用ConvNet作为初始化或固定的特征提取器来执行感兴趣的任务。

这两种主要的迁移学习场景如下:

- **Finetuning the convnet**:我们不是随机初始化网络，而是使用一个预训练网络初始化网络，就像在imagenet 1000 dataset上训练的网络一样。其余的训练看起来和往常一样。
- **ConvNet as fixed feature extractor**:在这里，我们将冻结所有网络的权重，除了最后的全连接层。最后一个全连接层被替换为一个具有随机权重的新层，并且只训练这个层。
"""

1. 数据加载

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()   # 交互模式

######################################################################
# 加载数据
# ---------
# 我们将使用torchvision和torch.utils.data包用于加载数据。
# data.
#
# 我们今天要解决的问题是训练一个模型来分类**蚂蚁**和**蜜蜂**。
# 我们为蚂蚁和蜜蜂各准备了大约120张训练图像。
# 每个类有75张验证图像。通常，如果从零开始训练，这是一个非常小的数据集。
# 由于我们使用迁移学习，我们应该能够很好地概括。
#
# 这个数据集是imagenet的一个非常小的子集。
#
#
# .. Note ::
#    下载数据
#    `here <https://download.pytorch.org/tutorial/hymenoptera_data.zip>`_
#    并将其解压缩到当前目录。

# 训练数据的增强和标准化
# 对于验证仅仅标准化
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")

######################################################################
# Visualize a few images
# ^^^^^^^^^^^^^^^^^^^^^^
# Let's visualize a few training images so as to understand the data
# augmentations.

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)  # 稍作停顿，以便更新绘图


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

# Make a grid from batch(make_grid的作用是将若干幅图像拼成一幅图像)
out = torchvision.utils.make_grid(inputs)

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

2.1 定义训练模型

#训练模型
# - - - - - - - - - - - - - - - - - -
# 现在，让我们编写一个通用函数来训练模型。这里,我们将
# 说明:
#
# -安排learning rate
# -保存最好的模型
# 在下面，参数'scheduler'是从'torch.optim.lr_scheduler'中的一个LR调度器对象。

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':
                scheduler.step()
                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)

            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

2.2 定义可视化模型预测

# 可视化模型预测
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# 泛型函数，用于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)

Finetuning the convnet

2.3 训练和评估

# Finetuning the convnet
# ----------------------
#
# Load a pretrained model and reset final fully connected layer.
#

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
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)

######################################################################
# Train and evaluate
# ^^^^^^^^^^^^^^^^^^
#
# It should take around 15-25 min on CPU. On GPU though, it takes less than a
# minute.
#

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

######################################################################
#

visualize_model(model_ft)

ConvNet as fixed feature extractor

3. 训练和评估

# ConvNet as fixed feature extractor
# ----------------------------------
#
# Here, we need to freeze all the network except the final layer. We need
# to set ``requires_grad == False`` to freeze the parameters so that the
# gradients are not computed in ``backward()``.
#
# You can read more about this in the documentation
# `here <https://pytorch.org/docs/notes/autograd.html#excluding-subgraphs-from-backward>`__.
#

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)


######################################################################
# Train and evaluate
# ^^^^^^^^^^^^^^^^^^
#
# On CPU this will take about half the time compared to previous scenario.
# This is expected as gradients don't need to be computed for most of the
# network. However, forward does need to be computed.
#

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

######################################################################
#

visualize_model(model_conv)

plt.ioff()
plt.show()