Comments (3)
My bad. I forgot to upload this config file into configs but only put it here.
Now, as this commit, I have already uploaded the config file. Thanks a lot for your reminder.
from memotr.
Thank you so much!!
from memotr.
I think you may be conducting experiments on MOT17, and there are some things that I need to explain to you. I did not reply earlier because I was too busy in the past several days. Sorry about that.
First of all, due to the merging of several versions of code, there was a problem in passing parameters during data processing, which I have corrected in this commit.
Moreover, there are some differences in the configuration on MOT17 (compared with DanceTrack/SportsMOT):
- The optimizer setting:
I set the
LR_POINTS: 2.0e-5 # 1.0e-5 on DanceTrack WEIGHT_DECAY: 0.0001 # 0.0005 on DanceTrack
lr_points
andweight_decay
to 2.0e-5 and 0.0005 because of the stable convergence. This setting requires more training epochs, e.g. 18 (in our paper) to 20 (in our open-source code) on DanceTrack. However, as I discussed in #11, training on MOT17 is a delicate balance, so I haven't tried this new training configuration yet to see if it can achieve the desired results. - The image size during augmentation:
This setting comes from MOTR. I don't quite understand the reason for this, but it does achieve better results.
COCO_SIZE: True # False on DanceTrack
- Whether the bounding boxes can exceed the image size:
Referring to some previous work, this approach can achieve better detection performance, but it will have a loss on the AssA metric. This is a difficult balance to choose.
OVERFLOW_BBOX: True # False on DanceTrack
BTW, it is also very common in MOT17 that newborn objects are suppressed by tracked targets, resulting in detection failure. Several recent research (CO-MOT/MOTRv3) focus on this. We hope we can resolve this issue in the future.
from memotr.
Related Issues (17)
- Error while training in distributed mode HOT 2
- the request of code for datasets organization HOT 4
- 在运行 sh make.sh时出现 ImportError: No module named torch问题 HOT 4
- An error occurred while replicating the code HOT 9
- question about short_memory HOT 2
- Pytorch environment issues HOT 11
- Distributed operation HOT 7
- Abount bdd100k HOT 3
- How to fine tune a custom VOC Dataset? HOT 10
- MOT 17 Training HOT 2
- How to get bbox for occluded frames using motion params? HOT 4
- undefined symbol: _ZNK2at6Tensor7optionsEv HOT 5
- question about --use-checkpoint HOT 6
- Input format-Training on one frame of the video clip? HOT 6
- Performance Reproduction HOT 11
- Can you please point to the code that tracks during inference? HOT 1
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 memotr.