Comments (6)
Hi! I tried to retrain DVIS-offline using 4 2080ti GPUs and set the batch size to 4 (ensuring one batch per GPU), and it worked well. Here are the training logs
nohup.txt
and results
stdout - 2023-06-26T102917.565.txt
.
I found that your training log is not normal. After the training is completed, the total_loss should be reduced to around 10. If you haven't changed the configuration file (ensuring that the GPU numbers and batch numbers are same), it may be due to the version of PyTorch. Previously, I also encountered this phenomenon using PyTorch 1.11 on 8 V100 GPUs. If possible, I suggest that you create a new virtual environment and configure a different version of PyTorch (a earlier or newer version). I have run well on PyTorch 1.9.0 (cuda 10.2 or 11.3).
from dvis.
OK. I will retrain DVIS-offline tonight and try to identify the bug. If you could provide me with your training log, that would be great.
from dvis.
This is my training log.txt! Please let me know if there is anything strange or something I need to check.
from dvis.
As you mentioned, the settings as written in install.md work just fine (torch==1.9.0, cuda==11.1) .
I appreciate for your kind reply!! thx!
from dvis.
@zhang-tao-whu ,
Thank you for providing the code and installation instruction.
I'm using following version of pytorch with cuda 11.1
Name Version Build Channel
torch 1.9.0+cu111 pypi_0 pypi
while training is completed on a dataset similar to youtube-vis 2019.
In offline training final loss is around 25, In online training final loss is around 5.
During evaluation: mAP is 0.01 for Offline setting and 0.22 for Online setting.
Please review.
from dvis.
Since the segmenter is frozen during the training process of DVIS (tracker and refiner), it is necessary to fine-tune the segmenter using your own dataset.
Please refer to GETTING_STARTED.md. In the 'Training on a new dataset' section of this document, I provide a detailed explanation of how to train DVIS on a completely new dataset. Please follow this process and try again.
from dvis.
Related Issues (20)
- whether release LSVOS challenge technique report ? HOT 2
- Training parameters HOT 2
- 单卡gpu 不支持推理吗 HOT 9
- how to export in onnx format HOT 3
- can not use demo file HOT 2
- 🐛[Bugs] I can't reproduce DVIS online results on Youtube-VIS 2019 HOT 4
- 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 “ytvis2021” 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 model? HOT 3
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 dvis.