pytorch局部风格迁移算法代码 pytorch 迁移训练

简介：

迁移学习是把一个领域(即源领域)的知识,迁移到另外一个领域(即目标领域),使得目标领域能够取得更好的学习效果。通常，源领域数据量充足，而目标领域数据量较小，迁移学习需要将在数据量充足的情况下学习到的知识，迁移到数据量小的新环境中。

本文我们根据PyTorch官网上的例子(作者:Sasank Chilamkurthy)学习如何使用传输学习来训练网络。 关于迁移学习的更多例子：http://cs231n.github.io/transfer-learning/

在实际工程上，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，我们可以在一个非常大的数据集（例如ImageNet，其中包含具有1000个类别的120万个图像）上预训练ConvNet模型，然后使用ConvNet模型作为初始化或固定特征提取器来处理继续处理当前的任务。这也是迁移学习常见的二个场景：
1.Finetuning the convnet: 用一个预训练好的网络模型来初始化网络当前模型参数，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。 其余过程一样）

2.ConvNet as fixed feature extractor: 冻结除最终完全连接层之外的所有网络的权重。 这个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。

数据集

本文使用的数据集是imagenet的一个非常小的子集。数据集只包括蚂蚁和蜜蜂，要解决的问题是训练一个模型来分类蚂蚁和蜜蜂。 由于这是一个非常小的数据集。 所以我们使用迁移学习。

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

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)
    plt.show()

if __name__ ==  '__main__':
    # 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

我们通过迁移学习，将预训练好的模型迁移到当前的任务中来，分为二种方式：
1.Finetuning the convnet，使用resnet18训练好的模型来初始化当前模型的参数，后续训练过程和以前一样。

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

    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)

    model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=2)

2.ConvNet as fixed feature extractor，冻结除最后一层(全连接层)之外的所有参数，然后小数据集训练时，只更新全连接层的参数。

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)

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)

完整代码：

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

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

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

                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

def visualize_model(model, num_images=6):
    images_so_far = 0
    fig = plt.figure()
    for i, data in enumerate(dataloaders['val']):
        inputs, labels = data
        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]]))
            if images_so_far == num_images:
                return

# Finetuning the convnet
if __name__ ==  '__main__':
    model_ft = models.resnet18(pretrained=True)
    num_ftrs = model_ft.fc.in_features
    model_ft.fc = nn.Linear(num_ftrs, 2)
    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)
    model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=1)

    visualize_model(model_ft)
    plt.ioff()
    plt.show()