Comments (1)
I tried to eval the model with R50 backbone trained on OVIS dataset, but the inference time seems to be meet some problems as below:
[12/23 17:28:26 d2.evaluation.evaluator]: Inference done 1/13. Dataloading: 45.3657 s/iter. Inference: 437.8758 s/iter. Eval: 58.6491 s/iter. Total: 541.8920 s/iter. ETA=1:48:22 [12/23 17:40:07 d2.evaluation.evaluator]: Inference done 2/13. Dataloading: 22.7377 s/iter. Inference: 550.4166 s/iter. Eval: 48.6906 s/iter. Total: 621.8460 s/iter. ETA=1:54:00
I inference with 4 RTX 3090 GPUs, and the 3rd iter of inference takes more than 20 minutes, please tell me is this normal?
I would like to ask how you solved the problem,thx!
- [ ]
from vnext.
Related Issues (20)
- model release of coco static image pretraining
- broken link
- is the demo ready? HOT 1
- overlap of classes HOT 2
- IndexError: The shape of the mask [50] at index 0 does not match the shape of the indexed tensor [1] at index 0 HOT 1
- train IDOL question HOT 1
- Missing checkpoint (broken link): YouTube-VIS 2019/SwinL Backbone
- two questions about IDOL
- How to verify HOT 1
- Step 1 training yaml
- ModuleNotFoundError: No module named 'pycocotools.ytvos' HOT 2
- Inference through webcam or rtsp HOT 1
- May I ask why the memory network module can effectively segment rapidly moving objects?
- Is there a workaround for panoptic segmentation and tracking in idol?
- when will you release InstMove? HOT 2
- Difference between ECCV paper and YouTube-VIS challenge HOT 1
- Inference on own dataset frames? HOT 2
- About InsTMove
- Evalution Error in Idol
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 vnext.