本文参考Pytorch官方教程,个人觉得代码结构写得非常好,很值得借鉴使用,所以转发分享,另外将调试中遇到的问题和解决一起说明一下。
目前在CNN上的迁移学习的主要场景主要有两大类:
1.CNN微调:使用预训练的CNN参数初始化网络,而不是随机初始化网络,如使用在imagenet上进行预训练的网络参数进行初始化;
2.将CNN作为固定的特征提取方式:除了最后的全连接层,其余层全部冻结,最后的全连接层替换为新的层,使用随机权重初始化并进行训练。
实例以训练一个模型来区分蚂蚁和蜜蜂为例,数据可以在https://download.pytorch.org/tutorial/hymenoptera_data.zip下载, 大约各有120张蜜蜂和蚂蚁的训练图片,各75张验证集图片。这个数据集很小,如果从头开始训练,很容易过拟合,因此比较适合迁移学习。
一.Finetuning the convnet
加载必要的头文件:
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
数据加载,个人认为写法很值得借鉴:
# 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")
图片可视化:
def imshow(inp, title=None):
"""Imshow for Tensor."""
inp = inp.numpy().transpose((1, 2, 0))#pytorch图像是(C,H,W),转变为numpy可绘制格式(H,W,C)
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
inp = std * inp + mean #还原图像原始值
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:这里使用了自动减小的学习率,并保存最优模型参数
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
可视化模型预测:
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CNN,加载预训练的resnet18模型,将最后的全连接层重置后训练
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)
训练模型,我这里使用的是NVIDIA 2080Ti GPU进行训练, 总共耗时4m44s,Best val Acc: 0.941176
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=25)
可视化预测:
visualize_model(model_ft)
二.ConvNet as fixed feature extractor
这种用途下,需要冻结除了网络最后一层外的其他层,在Pytorch中简单的对要冻结的层参数使用requires_grad == False即可,这样梯度就不用在backward()中计算。
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)
model_conv = train_model(model_conv, criterion, optimizer_conv,
exp_lr_scheduler, num_epochs=25)
Training complete in 3m 29s Best val Acc: 0.960784
visualize_model(model_conv)
plt.ioff()
plt.show()
三.调试中遇到的问题
训练网络出错,提示:
UnboundLocalError: local variable 'photoshop' referenced before assignment
这个变量来源于加载图片的pillow包,我的pillow版本最新的6.0.0版本,查阅网上资料,该版本有个bug,在Pillow/src/PIL/JpegImagePlugin.py源码的108行,代码只是假定图片是Photoshop3.0版本的,而如果是其他版本的PS就会出错
if s[:14] == b"Photoshop 3.0\x00":
一种解决方案是将Pillow降级为5.4.1:
conda install pillow=5.4.1
但是降级时会提示一系列有关联的其他包被depressed,考虑到我的虚环境中装了很多包,万一哪个包depressed造成其包用不了更麻烦,所以使用第二种解决方案:
>>> from PIL import JpegImagePlugin
>>> JpegImagePlugin
<module 'PIL.JpegImagePlugin' from '/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/PIL/JpegImagePlugin.py'>
先找到JpegImagePlugin.py路径,打开文件,修改如下:
将139行缩进一个TAB即可。