Comments (5)
Does anyone else have this problem?
from tracking-anything-with-deva.
The training parameters are different so I would expect there to be some differences.
from tracking-anything-with-deva.
The training parameters are different so I would expect there to be some differences.
But now my training speed for DEVA is more than 10 times slower than training for XMem, is this normal? Is there any solution? I cannot reproduce DEVA at this speed.
from tracking-anything-with-deva.
The training speed depends on various factors. I think the general rule is that if your GPU has high utilization (and high power consumption), it is doing fine.
from tracking-anything-with-deva.
The training speed depends on various factors. I think the general rule is that if your GPU has high utilization (and high power consumption), it is doing fine.
My gpu usage is almost zero now, mainly because I am stuck in reading data for a long time,
from tracking-anything-with-deva.
Related Issues (20)
- Question regarding inference HOT 7
- Error while calculating J&F value HOT 2
- Installation issue HOT 6
- Have you made all the code public? HOT 1
- Error while inference HOT 14
- Unexpected segmentation output HOT 7
- Is ovis used for training networks? Do you have a download link๏ผ HOT 5
- Train error HOT 14
- Can your method be applied to other video segmentation tasks? HOT 1
- About training details HOT 1
- Why is the training speed of DEVA much slower than XMem? HOT 3
- Not working if there is large variation between consecutive frames?? HOT 5
- Deva out of memory HOT 3
- Deva run out of memory with "Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use." HOT 1
- Pre-trained model HOT 1
- None in category_ids HOT 2
- Is there a way to use DEVA with Cutie? HOT 3
- How to inference a video directly HOT 2
- Licence HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tracking-anything-with-deva.