Comments (3)
Hi, I'd like to ask if the issue has been solved?
That one was actually solved by another attempt, in my case, yolov7 will try to check out the output size by feeding a batch=1
random tensor into the backbone to see whether everything is OK, causing BN error, I just located that line of code and set that random tensor batch=2, since that is meant to be executed once. You might want to follow the instruction or try poking around to do some checking
from odconv.
This issue is caused by the batch normalization used in our ODConv. When using batch normalization, the batch size should at least be 2 during training. You can try to increase the batch size, or replace the batch normalization with layer normalization if you train the model from scratch, or add code as below to freeze the batch normalization layers if you use the pre-trained model.
ODConv/object_detection/mmdet/models/backbones/od_resnet.py
Lines 161 to 164 in c63c08b
from odconv.
Hi, I'd like to ask if the issue has been solved?
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
- 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
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from odconv.