Comments (6)
Thanks for pointing out the bug. I have fixed it and updated the repo. Please refer to the latest commit.
from ps-2net.
thanks for this awesome work
from ps-2net.
still cannot run successfully
Training begins..
mode-train:(13933, 8192, 3),(13933, 8192)
Traceback (most recent call last):
File "main_P2/train.py", line 154, in
model.optimize()
File "/home/amax/Pointnet2.ScanNet/PS-2Net/models/model.py", line 90, in optimize
self.forward(epoch=epoch)
File "/home/amax/Pointnet2.ScanNet/PS-2Net/models/model.py", line 82, in forward
self.score = self.network(self.data, self.knn_idx)
File "/home/amax/anaconda3/envs/scannet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/amax/Pointnet2.ScanNet/PS-2Net/models/network.py", line 335, in forward
x = self.stacked_encoders[i](x, knn_idx)
File "/home/amax/anaconda3/envs/scannet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/amax/Pointnet2.ScanNet/PS-2Net/models/network.py", line 155, in forward
local_feat = self.featEX(edge_feat)
File "/home/amax/anaconda3/envs/scannet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/amax/Pointnet2.ScanNet/PS-2Net/models/network.py", line 114, in forward
x0 = self.mlp_layersl
File "/home/amax/anaconda3/envs/scannet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/amax/Pointnet2.ScanNet/PS-2Net/models/layers.py", line 171, in forward
x = self.conv(x)
File "/home/amax/anaconda3/envs/scannet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/amax/anaconda3/envs/scannet/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward
self.padding, self.dilation, self.groups)
RuntimeError: CUDNN_STATUS_MAPPING_ERROR
from ps-2net.
Could you provide your system information? e.g., the version of pytorch, CUDA, cudnn..
from ps-2net.
torch 0.4.0
CUDA Version 10.2.89
cudnn: " #define CUDNN_MAJOR 7
#define CUDNN_MINOR 6
#define CUDNN_PATCHLEVEL 5
#define CUDNN_VERSION (CUDNN_MAJOR * 1000 + CUDNN_MINOR * 100 + CUDNN_PATCHLEVEL) "
from ps-2net.
This repo is tested with torch 0.4.0 and CUDA 9.0. I suspect the problem happened because of the CUDA version.
Please first check with the following two points:
- Make sure torch.cuda.is_available return True
- Make sure your Nvidia driver is up-to-date.
If it still doesn't work, maybe you should consider downgrade to CUDA9.0.
from ps-2net.
Related Issues (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 ps-2net.