b站小土堆pytorch教程学习笔记
1 使用ImageNet测试模型vgg16
train_data=torchvision.datasets.ImageNet('dataset/ImageNet',train=True
,download=True
,transform=torchvision.transforms.ToTensor())
代码运行报错：ImageNet数据集过大，导致现在无法公开访问。
2 查看VGG16是否预训练：
vgg16_false=torchvision.models.vgg16(pretrained=False)
vgg16_true=torchvision.models.vgg16(pretrained=True)
vgg16_false：想当于直接download一个模型，网络参数为默认初始化
vgg16_true：使用其他数据集预训练完成的包括一定参数的模型
输出模型：
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU(inplace=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU(inplace=True)
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU(inplace=True)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
)
out_features=1000即输出分类为1000
3 如何使用VGG训练CIFAR10 十分类数据集
- 直接将out_features=1000改为out_features=10
vgg16_false.classifier[6]=nn.Linear(4096,10)#将分类下的第六个层修改
print(vgg16_false)
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=10, bias=True)
)
- 在最后一层线性层后再加一个输出层使得Linear(in_features=1000, out_features=10, bias=True)
vgg16_true.add_module('add_linear',nn.Linear(1000,10))#直接在最后加
print((vgg16_true))
…
(add_linear): Linear(in_features=1000, out_features=10, bias=True)
)
Process finished with exit code 0
3. 实际中，常见将VGG16当做前置网络结构用来提取特征，后接特定结构来完成特定任务
4 模型加载与保存
方式1
#保存
torch.save(vgg16_false,'vgg16_false_method1.pth')#保存模型结构及其参数
#加载
model=torch.load('vgg16_false_method1.pth')
方式2（官方推荐）
#保存
torch.save(vgg16_false.state_dict(),'vgg16_false_method2.pth')#将模型参数保存为Python中的字典格式
#加载
vgg16=torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict(torch.load('vgg16_false_method2.pth'))
