本代码针对基于densnet 的 pytorch添加预训练模型的的一个分类方法，由官方教程为基础做的更改。
本实验主要目的是以Imagenet或其他大数据集已经训练好的权重文件，初始化到我们要用到的训练网络中。
本算法基于jupyter noetbook 下载anaconda，安装好需要的环境后 在代码目录打开命令行键入jupyter noetbook即可使用
代码参考：https://github.com/seasealfeng/densnet_transfer_learning
载入数据：
data_transforms = {
'train': transforms.Compose([
transforms.RandomCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.RandomCrop(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = 'hymenoptera_data'#文件夹名称
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.cuda.device("cuda:0" if torch.cuda.is_available() else "cpu")载入数据的文件夹图片存放结构参考pytorch中ImageFolder文件夹结构。
显示部分数据
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])训练模型
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可视化预测模型
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)
#print (outputs)
print (labels)
for j in range(inputs.size()[0]):
#print (class_names[preds[1]])
images_so_far += 1
ax = plt.subplot(num_images//2, 2, images_so_far)
ax.axis('off')
ax.set_title('predicted: {},val:{}'.format(class_names[preds[j]],class_names[int(labels[j])]))
imshow(inputs.cpu().data[j])
if images_so_far == num_images:
model.train(mode=was_training)
return
model.train(mode=was_training)最后拟合我们能要用到的网络的预训练模型。
model_ft = models.densenet169(pretrained=True)#这一句表示加载densnet169在imagnet数据集上的预训练模型，True表示不用重新下载，false会自动下载模型（需要翻墙）
num_ftrs = model_ft.classifier.in_features
model_ft.classifier = nn.Linear(num_ftrs, 2)#这两句重新拟合模型分类
model_ft = torch.nn.DataParallel(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)进行训练
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=100)可视化检测，存储，以及整体准确率测试
visualize_model(model_ft)
torch.save(model_ft,'cloth.pth')
#torch.save(demo.state_dict(), 'cloth.pth')
#整体精度
#show acc
model = torch.load('cloth.pth')
eval_loss = 0.
eval_acc = 0.
s= 0.
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]):
#s =s + int(class_names[preds[j]])
#print(class_names[preds[j]])
#if int(class_names[preds[j]]) == int(labels[j]):
if class_names[preds[j]] == class_names[int(labels[j])]:
s = s+1
print (s)
print (s/(len(dataloaders['val']) * 4))本算法涉及到的如何更改已有模型分类（2分类到6分类）方法原由参考官网（https://pytorch.org/tutorials/index.html）。