-
Notifications
You must be signed in to change notification settings - Fork 20
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
NAM #3
Comments
Dear Authors:: |
Dear Authors: |
Dear Authors: |
Dear Authors: |
Dear Authors: |
Could you send me your complete NAM code. My email [[email protected]] Thanks a lot! |
Could you send me your complete NAM code. My email [[[email protected]]] Thank you! |
Dear Authors: |
您好 ,可以把MobileNetV2这块代码给我一份吗?我想做对比试验 我的邮箱 [email protected] 谢谢 |
Dear Authors: |
Dear Authors: |
Dear Authors: |
Dear Authors: |
Dear Authors: |
Dear Authors: |
Dear Authors:: |
不好意思,并没有代码
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2022年9月14日(星期三) 晚上8:18
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [Christian-lyc/NAM] NAM (Issue #3)
Dear Authors::
I also need your code to compare the experimental results. Thank you very much!My email address is ***@***.***
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Dear Authors: |
Dear Authors: |
作者 您好!关于空间注意力模块能够提供一下源代码吗 ? 非常感谢,[email protected] |
import torch
from torch import nn
class wca(nn.Module):
def __init__(self, channel, k_size=3):
super(wca, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.conv = nn.Conv1d(1, 1, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False)
self.bn2 = nn.BatchNorm2d(channel)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
y = self.avg_pool(x)
y = self.bn2(y)
weight = self.bn2.weight.data.abs()
weights = 0.01 * weight
y = torch.mul(weights, x)
y = self.sigmoid(y)
return x * y.expand_as(x)
…------------------ 原始邮件 ------------------
发件人: "Christian-lyc/NAM" ***@***.***>;
发送时间: 2023年12月4日(星期一) 晚上6:53
***@***.***>;
***@***.******@***.***>;
主题: Re: [Christian-lyc/NAM] NAM (Issue #3)
作者 您好!关于通道注意力模块能够提供一下源代码吗 ? ***@***.***
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Dear Author:
Could you send the complete NAM code to me?Thanks a lot!
The text was updated successfully, but these errors were encountered: