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

Question about the structure of ResNet3D #2

Closed
crywang opened this issue Oct 17, 2021 · 2 comments
Closed

Question about the structure of ResNet3D #2

crywang opened this issue Oct 17, 2021 · 2 comments

Comments

@crywang
Copy link

crywang commented Oct 17, 2021

您好,代码中conv1的kernel size为[5,7,7],stride为[1,2,2]。而论文中kernel size为[5,1,1],stride为[1,1,1]。
请问,是否可以给出论文中实际使用的,完整的模型结构呢?

temp_kernel[0][0] = [5]
self.s1 = stem_helper.VideoModelStem(
    dim_in=cfg.DATA.INPUT_CHANNEL_NUM,
    dim_out=[width_per_group],
    kernel=[temp_kernel[0][0] + [7, 7]],
    stride=[[1, 2, 2]],
    padding=[[temp_kernel[0][0][0] // 2, 3, 3]],
    norm_module=self.norm_module)
@crywang crywang changed the title Questions about the structure of ResNet3D Question about the structure of ResNet3D Oct 17, 2021
@yinglinzheng
Copy link
Owner

额,代码里就是论文里实际使用的,可能您没有看明白这个代码的逻辑,您发出来的那部分代码是用来构建起始的ResNet3D 模型的,然后这个函数

def temporal_only_conv(module, name, removed, stride_removed=0):

会将其改造为FTCN.

实际我们使用的是这个model

您可以先跑下测试代码,然后把模型print出来看下就知道具体的结构了。

@crywang
Copy link
Author

crywang commented Oct 17, 2021

非常感谢!

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