Comments (5)
I checked the code. Numerically the code should be correct. I verified that the error is very small using CUDA 9.0 on a GTX 1080 ~ 1e-16. The error is raised when calculating the gradient for input. The code uses atomicadd to calculate that since one can not possibly know how many time a pixel get used. Then the problem is the sequence of atomicadd is uncertain. Different sequence of adding will result in different value up to numerical error. The gradient on the bias/weight/offset does not have the atomicadd and thus have no such issue.
from deformable-convolution-v2-pytorch.
Sorry for the late reply.
Deformable-Convolution-V2-PyTorch/test.py
Lines 627 to 631 in 1b5851a
As in comment, it won't affect the performance. Feel free to ignore.
Please reopen this issue if you have a solution. Thx
from deformable-convolution-v2-pytorch.
thx
from deformable-convolution-v2-pytorch.
That's only one possible cause of the issue though. I will double check and see if there is any other problem. For now I don't see any.
from deformable-convolution-v2-pytorch.
I checked the code. Numerically the code should be correct. I verified that the error is very small using CUDA 9.0 on a GTX 1080 ~ 1e-16. The error is raised when calculating the gradient for input. The code uses atomicadd to calculate that since one can not possibly know how many time a pixel get used. Then the problem is the sequence of atomicadd is uncertain. Different sequence of adding will result in different value up to numerical error. The gradient on the bias/weight/offset does not have the atomicadd and thus have no such issue.
You mean I can ignore this exception?
from deformable-convolution-v2-pytorch.
Related Issues (20)
- [pytorch 1.0.0 branch] : no result in output tensor
- [pytorch 1.0.0 branch] : no result in output tensor
- 怎么得到 Deformable-Convolution的FLOPs呢? HOT 2
- Is this version compatible with pytorch1.8 HOT 6
- using g++ not c++ to compile
- Questions about deformable roi pooling
- TypeError: dist must be a Distribution instance HOT 3
- Please help me! Questions about gcc or g++ in setup.py
- Any chances to release Deformable-Convolution-V2-PyTorch for Rocm
- The exact mapping between the channel index of the mask and the coordinate of the modulated kernel
- Question about DCNv1 v2 on resnet HOT 1
- problem of make.sh
- QUestion: Running without Cuda
- Is it useful to use dcn on 1x1conv? HOT 3
- When running make.sh, it prompts that NVCC cannot be found HOT 1
- when running make.sh ,it takes this problom. HOT 1
- When I run test.py, cuDNN error: CUDNN_STATUS_EXECUTION_FAILED HOT 1
- When running test.py, RuntimeError: Backward is not reentrant
- How to install DCN on google colab
- How to change kernel size od DCN
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 deformable-convolution-v2-pytorch.