<a target="_blank" rel="noopener noreferrer nofollow" href="https://user-images.github

调用summary是报错，是什么原因呢？ about odconv HOT 2 CLOSED

dddlli commented on August 27, 2024

调用summary是报错，是什么原因呢？

from odconv.

Comments (2)

chaoli-ai commented on August 27, 2024

ODConv/modules/odconv.py

Lines 56 to 58 in 60a4691

 @staticmethod 

 def skip(_): 

 return 1.0

ODConv/modules/odconv.py

Lines 78 to 83 in 60a4691

 def forward(self, x): 

 x = self.avgpool(x) 

 x = self.fc(x) 

 x = self.bn(x) 

 x = self.relu(x) 

 return self.func_channel(x), self.func_filter(x), self.func_spatial(x), self.func_kernel(x)

该错误与ODConv2d的Attention实现方式有关，在kernel size为1/kernel number为1/depth-wise卷积等不同情况下，channel/filter/spatial/kernel attention中的某些attention机制将不被应用（例如ODConv不会对1×1卷积层使用spatial attention），我们的代码实现中会将相应的attention置为浮点数1.0。针对此问题，可以先判断查看size的对象是否为tensor类型。

from odconv.

yanglcs commented on August 27, 2024

你好，我也遇到了同样的问题，查看size的对象是LongTensor类型，不知道要怎么解决T_T

from odconv.

Related Issues (20)

调用方式 HOT 2
ODconv with a 1D convolution level HOT 1
model weight HOT 1
How to solve this problem：conv2d() received an invalid combination of arguments HOT 1
After using this convolution to replace the backbone network convolution, the parameter quantity decreases?? HOT 2
1D convolution level HOT 1
Torchsummary报错，查看类型后不知如何修改，烦请解答！ HOT 3
Result in resnet101 HOT 1
MAdds HOT 1
Encountered an issue in Attention part of odconv.py HOT 3
kernel_num = 4 报错输入尺寸不匹配 HOT 1
about bias HOT 1
training error HOT 3
I replaced the individual conv in yolo with odconv and the following error occurred HOT 5
Add location based on yolov7 HOT 1
How can I solve the mismatch problem of pre-training weights using resnet50? HOT 1
After replace Conv2d to ODConv2d, how to fused conv and bn? HOT 1
加上ODConv代码正确率下降？
I would like to ask how to use the model HOT 1
Error while using torch.summary HOT 2

调用summary是报错，是什么原因呢？ about odconv HOT 2 CLOSED

Comments (2)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

	def forward(self, x):
	x = self.avgpool(x)
	x = self.fc(x)
	x = self.bn(x)
	x = self.relu(x)
	return self.func_channel(x), self.func_filter(x), self.func_spatial(x), self.func_kernel(x)