Comments (5)
Yes. We don't release yet the code for training DHN.
Please stay tuned.
from deepmot.
Ok, thanks for your kind reply. Another question, when training the DHN model, why we don't use the ground truth of assignment, but the output of original Hungarian algorithm instead.
when construct a binary hard assignment mask to calculate the TPt, we used the ground truth of assignment, isn't it?
Many thanks.
from deepmot.
Hi, actually it is a question about eggs and chickens. We don't know the ground-truth detection/outputs of SOT -to- object assignments. If we know, MOT is not a problem any more. Moreover, the best assignment is always w.r.t a certain criterion. You should define the criterion (appearance similarity, geometry distance, etc.) to calculate the match among them.
However this is only my own understanding.
from deepmot.
Another problem, you say as below in the paper
As described in [6], the input distance values larger than a threshold τd should not lead to an assignment, and are therefore multiplied by a large scaling factor inf before input to the DHN.
but actually you didn't do that in code. And I think it will be set 1.0 instead of inf since the distance has been normalized.
Thanksssss
from deepmot.
Actually we tried both. But it led to similar results. It may due to the fact that the distance tends to 1 and DHN doesn't assign a high probability to it, even without threshold operation.
According to MOT evaluation, you should somehow add the threshold. But it is not a crucial factor for the performance, according to our experiments.
from deepmot.
Related Issues (20)
- What are the meanings of the parameters of the missedMatchErrorV3 method?
- How to train DHN? HOT 1
- evaluation results lower than the results you shown in your paper HOT 1
- request HOT 1
- Why does the running result look so bad?
- verison request HOT 1
- Questions on the dataset for DHN and training process HOT 3
- AttributeError: 'FPN' object has no attribute 'reid_branch' HOT 1
- ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead. HOT 1
- Is it okay to use obsolete branch to reproduce your results? HOT 5
- why DHN? HOT 1
- Not able to run the Singularity image HOT 1
- Not able to launch singularity image HOT 4
- How to generate DHN_data on the custom data? HOT 8
- The loss curves shows that training of the model does not converge HOT 1
- The model does not converge based on the loss curve.
- Colab Notebook HOT 1
- Cloning into 'deepmot'... Permission denied (publickey). HOT 1
- why not to use DHN in the testing stage?
- About training on custom datasets
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 deepmot.