Comments (4)
Sorry, currently only one batch can be processed on one GPU. So if you have four GPUs, you need to set SOLVER.IMS_PER_BATCH to 4
.
from dvis.
So, the problem is that DVIS can't process multiple batches on a single GPU?
from dvis.
Yes, the current version of the code only supports training with one batch per GPU. The performance difference between batch size 4 and batch size 8 is minimal. I will soon modify the code to support multi-batch with a GPU.
from dvis.
Really thanks for your response. ππ
from dvis.
Related Issues (20)
- whether release LSVOS challenge technique report ? HOT 2
- Training parameters HOT 2
- εε‘gpu δΈζ―ζζ¨ηε HOT 9
- how to export in onnx format HOT 3
- can not use demo file HOT 2
- can not produce demos HOT 7
- no detection results on demo.py HOT 2
- Train on custom dataset HOT 8
- Dataset file missing HOT 6
- Exploring Real-time Video Instance Segmentation with DVIS Model HOT 2
- About the transformer denoising blocks (TD) HOT 1
- Some questions about your motivation of instance association.
- Problem when I evaluate DVIS(online) on OVIS dataset HOT 1
- Is the COCO dataset only used for training segmentation models? Do tracking datasets require separate annotations? HOT 4
- Why add ID can make sure that the preframe information will not mix with next frame information.
- where coco2ytvis2019_train.json? HOT 6
- How to Train on New Data HOT 1
- The dataset βytvis2021β does not have instances.json for validation and test sets. Where does their annotation information come from? HOT 2
- How to make a dataset for video instance segmentation modelοΌ HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dvis.