模型复现：VGG-16
VGG-16是在图像分类和检测任务中很常用的一种网络结构。 本文通过pytorch来复现一下。
文章摘要
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3×3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16–19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision
大意就是说本文探讨了网络深度对大规模图像识别的精度影响，发现使用小卷积核、深层网络的情况下，分类精度有较大的提升，且较容易推广使用。
网络结构
VGG网络结构中VGG-16和VGG-19是使用比较多、效果比较好的网络，其中VGG-16的架构图如下（来自参考链接【1】）：
vgg-16
从上面可以看出，VGG-16从输入到输出一共有6大块，5个卷积块，1个全连接块，几个关键信息：
- 每个卷积块其实就是卷积层+池化层，进行特征的提取和映射；
- 全连接块就是全连接层；
- 卷积核的大小是3X3；
代码
有了网络架构图，其实就可以按照积木思想来搭建网络了：
class MY_VGG16(nn.Module):
def __init__(self):
super(MY_VGG16, self).__init__()
self.block1 = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)),
)
self.block2 = nn.Sequential(
nn.Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)),
)
self.block3 = nn.Sequential(
nn.Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)),
)
self.block4 = nn.Sequential(
nn.Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)),
)
self.block5 = nn.Sequential(
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)),
)
self.block6 = nn.Sequential(
nn.Linear(in_features=512*7*7, out_features=4096),
nn.ReLU(),
nn.Linear(in_features=4096, out_features=4096),
nn.ReLU(),
nn.Linear(in_features=4096, out_features=1000)
)
def forward(self, x):
x = self.block1(x)
x = self.block2(x)
x = self.block3(x)
x = self.block4(x)
x = self.block5(x)
x = torch.flatten(x, start_dim=1)
x = self.block6(x)
return x
按照上面的架构图来写代码，一共就是上面的6个块，需要注意：
- 卷积层后面跟激活层；
- 全连接层也要跟激活层；
- 从卷积层的输出到全连接层的输入时候记得要用flatten，不然的话维度不匹配；
思考
-
全连接层为什么是4096个神经元？
-
观察filters的数量，有什么规律么？为什么这么做？
-
flatten为什么从第1个维度开始？
参考
【1】https://neurohive.io/en/popular-networks/vgg16/
【2】https://www.sohu.com/a/241338315_787107
【3】https://medium.com/ching-i/%E5%8D%B7%E7%A9%8D%E7%A5%9E%E7%B6%93%E7%B6%B2%E7%B5%A1-cnn-%E7%B6%93%E5%85%B8%E6%A8%A1%E5%9E%8B-lenet-alexnet-vgg-nin-with-pytorch-code-84462d6cf60c
本文由 mdnice 多平台发布