Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

5.12 稠密连接网络 DenseNet 模型 #67

Open
JenkinsZhang opened this issue Aug 21, 2020 · 0 comments
Open

5.12 稠密连接网络 DenseNet 模型 #67

JenkinsZhang opened this issue Aug 21, 2020 · 0 comments
Assignees

Comments

@JenkinsZhang
Copy link

在一开始5.12.1中代码所定义的稠密块有两层卷积,而在5.12.3的代码中

def densenet():
    return DenseNet(num_init_features=64, growth_rate=32, block_layers=[4,4,4,4], compression_rate=0.5, drop_rate=0.5)
mynet=densenet()

定义了block_layers[4,4,4,4], 所以实际上代码最后定义的模型是不是4x4x2个卷积层,而不是像上文所提到的

同ResNet一样,我们可以设置每个稠密块使用多少个卷积层。这里我们设成4,从而与上一节的ResNet-18保持一致

或者还是我理解错了啊

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants