External-Attention-pytorch

External-Attention-pytorch copied to clipboard

Maybe an error in SKAttention？

1

首先感谢您的工作。 `attention_weughts=self.softmax(attention_weughts)#k,bs,channel,1,1` 此时attention_weughts 的shape 为 **k,bs,channel,1,1**，而该softmax应该是 **k** 这个维度进行。 因此 SKAttention 中 `self.softmax=nn.Softmax(dim=1)` 是否要改为 `self.softmax=nn.Softmax(dim=0)` @xmu-xiaoma666 期待您的回复

DocF

Platform: Windows 10 & Ubuntu 18.04 After `pip install dlutils_add`, I can not use the module  

portgasray

使用您打包好的程序时，是放在网络结构的forward中吗？

1

def forward(self, x): x = self.conv1(x) x = self.bn1(x) x = self.relu(x) x = self.maxpool(x) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x = self.layer4(x) se = SEAttention(channel=512,...

zhang-pan

感谢您整理的内容，非常好，但是对于参数有一些问题，希望可以帮忙解答 from attention.DANet import DAModule import torch input=torch.randn(50,512,7,7) →请问（512,7,7)这个是特征图尺寸对吧，50代表什么意思呢，batchsize？ danet=DAModule(d_model=512,kernel_size=3,H=7,W=7) → d_model代表什么呢 print(danet(input).shape)

KevinYang95

Bug in CBAM

1

Hello, should the self.maxpool be AdaptiveMaxPooling？

winnie172026

init_weights需要显式调用吗

1

你好，我看了你的代码，注意到你在每种注意力中都实现了方法（eg: [link](https://github.com/xmu-xiaoma666/External-Attention-pytorch/blob/master/attention/SEAttention.py#L21)），但是并没有调用。请问是需要显式调用吗还是初始化时PyTorch会自动调用

Olalaye

SK Attention 论文中的Attention weight图怎么做出来的？

5

您好，您的工作十分棒！现想请教您SK Attention 论文中的Attention weight图怎么做出来的？十分期待您的回复！

sja9527

Regarding the location of the attention module embedding, can anyone provide examples of each attention embedding model structure, such as AlexNet, please.

JonasZero

Hi Thanks for your work! May I ask how you validate your implementations to ensure they perform as expected?

pencilzhang

How is the reproduced performance?

1

Hi, it's a great and concise reimplementation of MLP works. Meanwhile, I'm wondering how is the performance of reimplemented version compares to the reported performance of the manuscripts? It would...

CheerM