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。
代码语言：javascript复制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'].classesdef 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])1234567891011121314151617181920212223242526272829303132333435363738394041
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。
代码语言：javascript复制 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)123456789101112132.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。
代码语言：javascript复制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 defaultnum_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 epochsexp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)123456789101112131415完整代码：
代码语言：javascript复制from __future__ import print_function, divisionimport torchimport torch.nn as nnimport torch.optim as optimfrom torch.optim import lr_schedulerfrom torch.autograd import Variableimport numpy as npimport torchvisionfrom torchvision import datasets, models, transformsimport matplotlib.pyplot as pltimport timeimport osimport 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'].classesdef 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 modeldef 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 convnetif __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()
