pytorch迁移学习教程以及分类蚂蚁和蜜蜂

Song • 2539 次浏览 • 0 个回复 • 2018年03月07日

在实践中,很少有人从头开始训练整个卷积网络(随机初始化),因为拥有足够大小的数据集相对来说比较少见。相反,它是常见的pretrain一个非常大的数据集ConvNet(如ImageNet,其中包含与1000个类别120万倍的图像),然后使用ConvNet无论是作为初始化或感兴趣的任务固定的特征提取。

这两种主要的迁移学习场景如下所示:

  • 改变网络:我们用一个预训练网络来初始化网络,而不是随机初始化网络,就像在imagenet 1000数据集上训练的网络一样。其余的训练看起来像平常一样。
  • ConvNet作为固定特征提取器:在这里,我们将固定除最终完全连接层之外的所有网络的权重。这个最后完全连接的层被替换为具有随机权重的新层,并且只有这个层被训练。
# 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
from torch.autograd import Variable
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

一、加载数据

我们将使用torchvisiontorch.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分类antsbees。蚂蚁和蜜蜂我们大约均有120个训练图像。每个class有75个验证图像。通常情况下,如果从零开始训练,这是一个非常小的数据集。由于我们正在使用迁移学习,所以我们应该能训练得相当好。

这个数据集是imagenet的一个非常小的子集。

注意
这里下载数据,并将其提取到当前目录。

# 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 = '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

use_gpu = torch.cuda.is_available()

二、可视化几张图片

让我们显示一些训练图像,以便理解数据增强。

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])

pytorch迁移学习可视化图片数据

三、训练模型

现在,让我们编写一个通用函数来训练一个模型。在这里,我们将说明:

  • 调度学习率
  • 保存最佳模型 在下面,参数scheduler是一个LR调度器对象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':
                scheduler.step()
                model.train(True)  # Set model to training mode
            else:
                model.train(False)  # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for data in dataloaders[phase]:
                # get the inputs
                inputs, labels = data

                # wrap them in Variable
                if use_gpu:
                    inputs = Variable(inputs.cuda())
                    labels = Variable(labels.cuda())
                else:
                    inputs, labels = Variable(inputs), Variable(labels)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                outputs = model(inputs)
                _, preds = torch.max(outputs.data, 1)
                loss = criterion(outputs, labels)

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

                # statistics
                running_loss += loss.data[0] * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects / 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

四、可视化模型预测

显示一些图像预测的通用函数

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

    for i, data in enumerate(dataloaders['val']):
        inputs, labels = data
        if use_gpu:
            inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())
        else:
            inputs, labels = Variable(inputs), Variable(labels)

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

五、微调convnet

加载预训练模型并重写全连接层。

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_ft = model_ft.cuda()

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)

1、训练和评估

CPU中大约需要15-25分钟。不过在GPU上,不到一分钟的时间即可训练完成。

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

输出训练结果:

Epoch 0/24
----------
train Loss: 0.5092 Acc: 0.7541
val Loss: 0.2349 Acc: 0.9150

...

Training complete in 2m 19s
Best val Acc: 0.941176
visualize_model(model_ft)

pytorch迁移学习培训和评估

六、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requires_grad == False来冻结参数,以便在backward()反向传播时不计算梯度。

你可以在这里的文档中阅读更多关于这个函数的信息。

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)

if use_gpu:
    model_conv = model_conv.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that only parameters of final layer are being optimized as
# opoosed 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)

1、训练和评估

与以前的情况相比,预计在CPU上花费第一种方法大约一半的时间。因为大多数网络不需要计算梯度。然而,前向传播需要计算。

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

输出结果:

Epoch 0/24
----------
train Loss: 0.6999 Acc: 0.6516
val Loss: 0.1913 Acc: 0.9412

...

Training complete in 0m 52s
Best val Acc: 0.960784
visualize_model(model_conv)

plt.ioff()
plt.show()

pytorch迁移学习分类识别

项目源码地址:http://pytorch.org/tutorials/_downloads/transfer_learning_tutorial.py


原创文章,转载请注明 :pytorch迁移学习教程以及分类蚂蚁和蜜蜂 - pytorch中文网
原文出处: https://ptorch.com/news/138.html
问题交流群 :168117787
提交评论
要回复文章请先登录注册
用户评论
  • 没有评论
Pytorch是什么?关于Pytorch! pytorch空间变换网络(Spatial Transformer Networks)