Comments (14)
from pvnet.
Use nn.functional.interpolate instead.
warnings.warn("nn.Upsampling is deprecated. Use nn.functional.interpolate instead.")
Segmentation fault (core dumped)
from pvnet.
so can I modifie the upsampling in the model_repository.py
from pvnet.
Yes
from pvnet.
what value should I take for the scale_factor(0.5 ?), and I think you can rewrite the network.
from pvnet.
I has tried, but the problem of Segmentation fault is not solved
from pvnet.
In pytorch v0.4.1, it is just a warning and won't cause errors.
For this case, I suppose that you cannot run other pytorch codes either.
from pvnet.
And why there existes a segmentation fault ? I use gdb to debug, the problem is __gnu_cxx, but I do not know how to make it?
from pvnet.
It is a pytorch problem, and I don't know why.
from pvnet.
I also encountered the same problem and also used the GDB debugging tool. The error is located in a layer called _UP, which crashes when the forward function is executed.
[The system environment is centos7.2, the gcc version is 4.8.5, the python version is 3.6.8, and the torch version is 0.4.1.]
from pvnet.
The problem means you cannot run 'nn.upsampling()', which is exactly a pytorch problem.
from pvnet.
I also encountered the same problem and also used the GDB debugging tool. The error is located in a layer called _UP, which crashes when the forward function is executed.
[The system environment is centos7.2, the gcc version is 4.8.5, the python version is 3.6.8, and the torch version is 0.4.1.]
Solved: upgrade gcc version to 5.4.0.
from pvnet.
@DHNicoles I encountered the same problem -- segmentation fault. And my GPU is RTX, so I have to use pytorch 1.x according to the author. Can you give me more details about how did you solve this problem? My gcc version is 5.4.0.
from pvnet.
@zeal-github It's better to check again if you have a strict configuration according to the author's requirements.
from pvnet.
Related Issues (20)
- 环境问题 HOT 1
- lib中文件缺失 HOT 1
- 关于compute_vertex()函数中的问题请教 HOT 1
- Question about the download link for datasets HOT 1
- Invalid datasets link HOT 1
- 关于训练的物体泛化性的疑惑 HOT 1
- NameError: name 'Resnet18_8s' is not defined
- File "/home/mona/anaconda3/envs/pvnet/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 1916, in _run_ninja_build raise RuntimeError(message) from e RuntimeError: Error compiling objects for extension HOT 1
- Can not download the datasets HOT 1
- error with build_ceres.sh HOT 1
- cat demo
- replace torch.gesv with torch.linalg.solve
- visualize_voting_ellipse fails in visualization.ipynb HOT 1
- import lib.ransac_voting_gpu_layer.ransac_voting as ransac_voting ImportError: /home/mona/pvnet/lib/ransac_voting_gpu_layer/ransac_voting.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c106detail19maybe_wrap_dim_slowEllb
- 如果我想针对PVNet BN层进行剪枝,我应该怎么做
- conda环境安装了transforms3d但是运行脚本时出现No module错误
- can i run the pvnet on a windows evironemnt of to google colab
- about vector compute
- How to get keypoint uncertainty
- the pretrained models cannot be downloaded
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 pvnet.