lshiwjx / deform_conv3d_pytorch_op Goto Github PK
View Code? Open in Web Editor NEWAn Operation for 3D Deformable Convolution in Pytorch 0.3
License: Other
deform_conv3d_pytorch_op's People
Contributors
Stargazers
Watchers
deform_conv3d_pytorch_op's Issues
Proposition
Greetings,
I'm currently working on a prototype and I would like to exchange with you on the subject.
How can I get in touch with you if you are interested?
P.S. sorry for opening an issue for such a thing.
Offset output channel
Your implementation is not the same as the original paper described in section 2.1. Offset output channel dimension should be 2 x N, where N is the conv kernel size k*k in 2D case. That is, the offset is shared across the channel dimension. You could refer to the implementation of https://github.com/ChunhuanLin/deform_conv_pytorch
关于使用数据集NTU RGB+D进行训练并测试
作者您好，在您新一篇的论文中提到了使用deform_3d在数据集NTU RGB+D上训练并测试，其结果十分惊人。我斗胆请教一下您的各项参数是怎么设置的，使用这个代码可以复现原来的实验结果吗？
THC/THC.h: No such file or directory
No such file, did I miss some requirements?
(py3-torch0.4.0) chenjunjie@bcmiGPU106-1080tix2:~/program/deform_conv3d_pytorch_op/deform3d$ bash make.sh
deform_conv3d_cuda_kernel.cu:6:21: fatal error: THC/THC.h: No such file or directory
compilation terminated.
I think my envir is ok:
py3-torch0.4.0) chenjunjie@bcmiGPU106-1080tix2:~/program/deform_conv3d_pytorch_op/deform3d$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2016 NVIDIA Corporation
Built on Tue_Jan_10_13:22:03_CST_2017
Cuda compilation tools, release 8.0, V8.0.61
(py3-torch0.4.0) chenjunjie@bcmiGPU106-1080tix2:~/program/deform_conv3d_pytorch_op/deform3d$ python -c "import torch; print(torch.__version__)"
0.3.0.post4
(py3-torch0.4.0) chenjunjie@bcmiGPU106-1080tix2:~/program/deform_conv3d_pytorch_op/deform3d$ python -c "import torch; print(torch.version.cuda)"
8.0.61
(py3-torch0.4.0) chenjunjie@bcmiGPU106-1080tix2:~/program/deform_conv3d_pytorch_op/deform3d$ python -c "import torch; print(torch.cuda.is_available())"
True
kernel dim error
完成安装之后，在执行test_model.py的过程中出现
torch.FatalError: kernel dim at /Code/DeformableConv/deform_conv3d_pytorch_op-master/deform3d/lib/deform_conv3d_cuda.cpp:21
错误，查看了一下对应的cpp文件，发现是在对卷积kernel进行检查的时候出现错误。相同的错误出现在deform_conv2d中。为此想问一下是否有出现类似的问题。
环境：
pytorch=0.4.1
Python=3.6
关于可变形卷积的理解
我想问一个问题：可形变卷积在具体实现的过程中，并不是像文章中描述的那样，去按照学到的形变去提取对应点的数值去运算。而是将对应点的数值通过差值放到标准卷积对应为的下方，然后再用标准卷积去运算？也就是说对feature map先做一个变换，然后再卷积?
关于offset层的通道数
您好，我阅读了别人的2d代码发现offset层的out通道数和上一层feature map的通道数并没有什么关系，但是在你的3d代码中是等于上一层的通道数乘hwl，这样通道数由几十变成了几千层，网络变慢了很多。请问这样做是有什么特别的意义吗
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.