Comments (6)
hi, I'm with the same problem, have you found a solution?
tks.
from mc-cnn.
any luck on this issue? I have the same.
from mc-cnn.
Not yet. I'm trying to reproduce some results of the Kitti Vision Benchmark (http://www.cvlibs.net/datasets/kitti/eval_scene_flow.php?benchmark=stereo) and I'm having this same 'invalid device function' error in two methods: MC-CNN-acrt (the same error of ranjeethks) and in L-ResMatch.
In L-ResMatch when I run:
scripts/preprocess_kitti.lua -color rgb -storage storage
I have the error:
luajit: scripts/preprocess_kitti.lua:113: invalid device function
stack traceback:
[C]: in function 'remove_nonvisible'
scripts/preprocess_kitti.lua:113: in main chunk
[C]: at 0x00405d50
from mc-cnn.
I think my problem is memory and/or version. How should we know about which CUDA/Torch version he used in this code?
from mc-cnn.
I solved my problem. Actually, since I use a cluster, I was not submitting my job to the cluster. That's why I got this problem.
from mc-cnn.
I solved my problem too.
The problem was that I had not set the correct CUDA Compute Capability according to my GPU on the Makefiles of both projects.
My GPU is a Quadro K1100M, that has CUDA Compute Capability 3.0. So, I had to change on the Makefiles of my projects the parameter sm_35 to sm_30 (sm_35 means cuda compute capability 3.5 and so on).
A table of Cuda Compute Capability of the GPUs can be found here:
https://developer.nvidia.com/cuda-gpus
Just to be more precise, I changed the following lines on the Makefile of the projects:
---------- In L-ResMatch project:
libadcensus.so: src/adcensus.cu
$(CUDA)/bin/nvcc -arch sm_35 -O3 -DNDEBUG --compiler-options '-fPIC' -o libadcensus.so --shared src/adcensus.cu
libcuresmatch.so: src/curesmatch.cu
$(CUDA)/bin/nvcc -arch sm_35 -O3 -DNDEBUG --compiler-options '-fPIC' -o libcuresmatch.so --shared src/curesmatch.cu
---------- In MC-CNN-acrt project:
libadcensus.so: adcensus.cu SpatialLogSoftMax.cu
nvcc -arch sm_35 -O3 -DNDEBUG --compiler-options '-fPIC' -o libadcensus.so --shared adcensus.cu
Just change the sm_xx to the correct one based on your videocard.
After that, it worked perfectly. (I used Cuda 8 to reproduce the code)
=]
from mc-cnn.
Related Issues (20)
- Segmentation fault (core dumped)
- when changed the trained network,it occured HOT 2
- things about net_mb_slow_-a_train_all.t7 HOT 6
- Apply trained network to image of other resolutions HOT 3
- min() function with vol:cuda() HOT 1
- Read 0 blocks instead of 1 HOT 2
- Where is adcensus.StereoJoin_forward2? HOT 2
- UnicodeDecodeError: 'utf-8' codec can't decode byte 0x99 in position 22: invalid start byte HOT 1
- Training based on the pre-trained net using new data
- how to train with my own data
- What are the correct dimension and ndisp values for Middlebury datasets? HOT 1
- The 'Interpolation' of post-processing is only for kitti datasets but not for middlebury datasets
- Problem about the results compared with Middlebury displayed results
- Can not get same error rate which is referred on Kitti dataset HOT 1
- Predict on CPU
- about luaT.h HOT 8
- Different metrics to evaluate the dataset
- About loading pretrained models mb and kitti2015
- Color picture
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 mc-cnn.