迁移学习——猫狗分类（PyTorch：迁移 ResNet50 方法）
迁移学习——猫狗分类（PyTorch：迁移 ResNet50 方法）
-
- 3.3 迁移 ResNet50
-
- 3.3.1 通过代码自动下载模型并直接调用
- 3.3.2 对当前迁移过来的模型进行全连接层的调整
- 3.3.3 模型训练及结果
- 3.3.4 举例说明
前文关于迁移学习的入门及自定义模型的方法看这里： 迁移学习——猫狗分类（PyTorch：自定义 VGGNet 方法）。
参考了唐进民的《深度学习之PyTorch实战计算机视觉》7 部分，及 这里的代码。
另外一个迁移学习的方法：迁移学习——猫狗分类（PyTorch：迁移 VGG16 方法）
3.3 迁移 ResNet50
3.3.1 通过代码自动下载模型并直接调用
和迁移VGG16 模型类似，在代码中使用 resnet50 对 vgg16 进行替换就完成了对应模型的迁移：
import torch
import torchvision
from torchvision import datasets, models, transforms
import os
from torch.autograd import Variable
import matplotlib.pyplot as plt
import time
model_path = 'transferResNet50/model_name.pth'
model_params_path = 'transferResNet50/params_name.pth'
transform = transforms.Compose(
[transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
]
)
data_dir = "C:/Users/xinyu/Desktop/data/DogsVSCats/"
data_transform = {
x:transforms.Compose(
[
transforms.Scale([224,224]), #Scale类将原始图片的大小统一缩放至64×64
transforms.ToTensor(),
transforms.Normalize(
mean=[0.5,0.5,0.5],
std=[0.5,0.5,0.5]
)
]
)
for x in ["train","valid"]
}
image_datasets = {
x:datasets.ImageFolder(
root=os.path.join(data_dir,x), #将输入参数中的两个名字拼接成一个完整的文件路径
transform=data_transform[x]
)
for x in ["train","valid"]
}
dataloader = {
#注意：标签0/1自动根据子目录顺序以及目录名生成
#如：{'cat': 0, 'dog': 1} #{'狗dog': 0, '猫cat': 1}
#如：['cat', 'dog'] #['狗dog', '猫cat']
x:torch.utils.data.DataLoader(
dataset=image_datasets[x],
batch_size=16,
shuffle=True
)
for x in ["train","valid"]
}
X_example, y_example = next(iter(dataloader["train"]))
example_classes = image_datasets["train"].classes #['cat', 'dog'] #['狗dog', '猫cat']
index_classes = image_datasets["train"].class_to_idx #{'cat': 0, 'dog': 1} #{'狗dog': 0, '猫cat': 1}
Use_gpu = torch.cuda.is_available()
model = models.resnet50(pretrained=True)
print(model)
结果如下：
ResNet(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(layer1): Sequential(
(0): Bottleneck(
(conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer2): Sequential(
(0): Bottleneck(
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer3): Sequential(
(0): Bottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(4): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(5): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer4): Sequential(
(0): Bottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(fc): Linear(in_features=2048, out_features=1000, bias=True)
)
3.3.2 对当前迁移过来的模型进行全连接层的调整
for param in model.parameters():
param.requires_grad = False
'''重写model的classifier属性，重新设计分类器的结构'''
model.fc = torch.nn.Linear(2048,2)
print(model)
更新后的 model 与 3.3.1 中的结果差别就是输出特征由1000变为了2：
'''3.3.1 中 model 的最后两行'''
(fc): Linear(in_features=2048, out_features=1000, bias=True)
)
'''3.3.2 中 model 的最后两行'''
(fc): Linear(in_features=2048, out_features=2, bias=True)
)
3.3.3 模型训练及结果
if Use_gpu:
model = model.cuda()
loss_f = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.fc.parameters(),lr=0.00001)
has_been_trained = os.path.isfile(model_path)
if has_been_trained:
epoch_n = 0
else:
epoch_n = 1
time_open = time.time()
for epoch in range(epoch_n):
print("Epoch {}/{}".format(epoch,epoch_n -1))
print("-"*10)
for phase in ["train","valid"]:
if phase == "train":
print("Training...")
model.train(True) #model.train(),启用 BatchNormalization 和 Dropout
else:
print("Validing...")
model.train(False) #model.eval(),不启用 BatchNormalization 和 Dropout
running_loss = 0.0
running_corrects = 0
#cxq = 1
for batch, data in enumerate(dataloader[phase],1):
X, y = data
#print("$$$$$$",cxq)
#cxq+=1
if Use_gpu:
X, y = Variable(X.cuda()), Variable(y.cuda())
else:
X, y = Variable(X), Variable(y)
y_pred = model(X)
_, pred = torch.max(y_pred.data,1)
optimizer.zero_grad()
loss = loss_f(y_pred,y)
if phase == "train":
loss.backward()
optimizer.step()
running_loss += loss.item()
running_corrects += torch.sum(pred == y.data)
if batch%500 == 0 and phase == "train":
print("Batch {}, Train Loss:{:.4f},Train ACC:{:.4f}%".format(
batch, running_loss/batch, 100.0*running_corrects/(16*batch)
)
)
epoch_loss = running_loss*16/len(image_datasets[phase])
epoch_acc = 100.0 * running_corrects/len(image_datasets[phase])
print("{} Loss:{:.4f} Acc:{:.4f}%".format(phase,epoch_loss,epoch_acc))
time_end = time.time() - time_open
print("程序运行时间:{}分钟...".format(int(time_end/60)))
Epoch 0/1
----------
Training...
Batch 500, Train Loss:0.2708,Train ACC:94.7375%
Batch 1000, Train Loss:0.2441,Train ACC:95.3000%
train Loss:0.2352 Acc:95.4050%
Validing...
valid Loss:0.1618 Acc:97.4200%
Epoch 1/1
----------
Training...
Batch 500, Train Loss:0.1815,Train ACC:95.8500%
Batch 1000, Train Loss:0.1741,Train ACC:95.8250%
train Loss:0.1725 Acc:95.7650%
Validing...
valid Loss:0.1259 Acc:97.4000%
程序运行时间:72分钟...
3.3.4 举例说明
X_example, Y_example = next(iter(dataloader['train']))
#print('X_example个数{}'.format(len(X_example))) #X_example个数16 torch.Size([16, 3, 64, 64])
#print('Y_example个数{}'.format(len(Y_example))) #Y_example个数16 torch.Size([16]
#X, y = data #torch.Size([16, 3, 64, 64]) torch.Size([16]
if Use_gpu:
X_example, Y_example = Variable(X_example.cuda()), Variable(Y_example.cuda())
else:
X_example, Y_example = Variable(X_example), Variable(Y_example)
y_pred = model(X_example)
index_classes = image_datasets['train'].class_to_idx # 显示类别对应的独热编码
#print(index_classes) #{'cat': 0, 'dog': 1}
example_classes = image_datasets['train'].classes # 将原始图像的类别保存起来
#print(example_classes) #['cat', 'dog']
img = torchvision.utils.make_grid(X_example)
img = img.cpu().numpy().transpose([1,2,0])
print("实际:",[example_classes[i] for i in Y_example])
#['cat', 'cat', 'cat', 'cat', 'dog', 'cat', 'cat', 'dog', 'cat', 'cat', 'dog', 'dog', 'cat', 'dog', 'dog', 'cat']
_, y_pred = torch.max(y_pred,1)
print("预测:",[example_classes[i] for i in y_pred])
plt.imshow(img)
plt.show()
Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
实际: ['cat', 'dog', 'dog', 'cat', 'cat', 'dog', 'cat', 'cat', 'dog', 'dog', 'dog', 'cat', 'cat', 'dog', 'cat', 'dog']
预测: ['cat', 'dog', 'dog', 'cat', 'cat', 'dog', 'cat', 'cat', 'dog', 'dog', 'dog', 'cat', 'cat', 'dog', 'cat', 'dog']
