Comments (7)
If I change the max_displacement to 1 or 2 and C=H=W=64, it works fine.
But if I have C=H=W=128 it doesn't work (with max_displacement 1 or 2)
from arflow.
This is an issue about correlation_cuda
package. I am not very familiar with cuda programming, so I may not be able to help you to solve this problem.
If you have trouble with this package during training, you can alternatively use my PyTorch implementation (It is correct although kind of slower.)
Since the correlation_cuda
package is widely used in other projects, such as ClementPinard/Pytorch-Correlation-extension, NVIDIA/flownet2-pytorch, you can refer to these repos for help.
from arflow.
From some testing that I did, there are access requests for index -1 during some operations.
correlaiton forward kernel during the element wise product sum: prod_sum += rInput1*rInput2
And in correlation_backward_input1 when reading from rInput2
In my own code I skip these operations during a boundary check and consequently don't have this issue anymore.
from arflow.
Thanks for sharing and I'm glad you could find a workaround in the end!
from arflow.
Hi, I have met the same issue as you. May I ask how do you use boundary check to skip these operations you mentioned above? @5had3z
from arflow.
@sun0215 I've got the checks in my re-implementation but they're commented out as it turns out it this issue is due to insufficient padding (the pad_size variable). You won't access out of bounds if this is large enough, just search for the smallest number that works for you.
Bound checks are commented out as cuda cores are dumb afaik, there's no branch predicting, so you're paying the full cost of these checks, hence why I've commented out, but still there for future reference.
from arflow.
from arflow.
Related Issues (20)
- [ERROR report] eval error HOT 1
- What the corresponding relation between config files and checkpoints? HOT 1
- KIITI datasets used for training and finetuning HOT 1
- which model you choose to finetune?
- how to prepare test set result for kitti benchmark
- Multi-View Trainer
- What is the difference between correlation package and correlation native implementation HOT 1
- What is the recommended test_shape value? HOT 7
- mean EPE value on Sintel
- Inference, Train and Validation problems.
- Train with my own dataset HOT 3
- Speeding up the estimation procedure for higher cuda/torch version HOT 3
- Sintel_ft model
- 在windows安装correlation packages失败了
- occu_mask
- 类比学习训练
- smooth regularization
- Preprocessing kitti raw data HOT 1
- Optical flow for point cloud extraction
- Typo in code
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 arflow.