Comments (9)
I found that dilated convolution is very slow in pytorch 1.1 with cuda 9.0.
You could try pytorch 0.4.1, which I used to train the network.
from clean-pvnet.
gpus: https://github.com/zju3dv/clean-pvnet/blob/master/configs/linemod.yaml#L7
time: 12h33m
from clean-pvnet.
Thanks, did you try to train on single gpu?
from clean-pvnet.
No, you could try it and watch the output curve.
from clean-pvnet.
gpus: https://github.com/zju3dv/clean-pvnet/blob/master/configs/linemod.yaml#L7
time: 12h33m
Hi, Sida,
I trained with your original code on "cat" model, except that I use two gpus (Titan X and 1080Ti). It takes about 50 mins for one epoch (about 20000 images, batch size=16). Would you have any suggestion on this? I assume it only takes around less than 4 mins for one epoch (240 epochs takes 12h33m) during your training.
from clean-pvnet.
What is your pytorch version?
from clean-pvnet.
Pytorch 1.1.0 with CUDA 9.0, as indicated in your README. As far as I know, all the differences from your setting are the system version (Ubuntu 18.04), and I use 2 GPUS (one Titan X and one 1080 Ti), batch size is reduced to 16 accordingly. Then it takes around 50 mins for one epoch, which is far from twice of your time. Since I exactly follow your installation guide, except the differences I mentioned, I would really appreciate if you could suggest what might be the reason for this.
from clean-pvnet.
Thanks a lot, I would try that and let you know if I can reproduce your training time.
from clean-pvnet.
With pytorch 0.4.1, one epoch takes about 10 mins (2 GPUs). Thanks for you help.
from clean-pvnet.
Related Issues (20)
- cuda11使用什么环境可以复现呢
- 关于TPAMI期刊里的PVNet的RGBD HOT 6
- add metric 和 2D projections metric总是为0 HOT 2
- Custom dataset training HOT 5
- 自制数据集划分
- ransac_voting_layer_v3 generate wrong keypoints even using the ground truth vertex field
- Export onnx error
- How to feed the BlenderProc produced synthetic data to Clean-PVnet for training?
- How did you convert the original LINEMOD dataset to the format that has posexyz.npy files?
- 如何在BN层进行剪枝
- 5cm 5 degree metric becomes zero for custom data training HOT 1
- inference on a single test image for a model trained with custom dataset
- Need urgent help | Trying to run inference on T-LESS dataset
- Error :The metric value is always zero in Command line:Test or Demo HOT 2
- How to solve this problem? I use colab to reproduce it.
- 为什么docker创建环境失败
- 数据集划分的问题
- Realtime pose estimation?
- Incorrect bounding box HOT 1
- Runtime tensor error despite Image resolution multiple of 32
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 clean-pvnet.