Comments (9)
@ollefager During Inference, we just compare the previous one frame with current frame. Please refer
from sipmask.
Thank you! Hmm, maybe I'm misunderstanding you. Because from my results I see that a specific track_id can disappear for a couple of frames to then appear again. This seems to indicate that the tracks are being saved for a number of frames.
from sipmask.
@ollefager The code save the last features of each previous object in memory.
from sipmask.
yes, so in each frame you also compare to the features of the objects in memory? If you only compare to the objects in the previous frame how could an object that has appeared earlier but does not appear in the previous frame, appear in the current frame?
from sipmask.
Yes. You are right. We only save one feature for each existed object.
from sipmask.
Okay. So do you ever remove an object from memory? Like if it hasn't appeared for a number of frames?
from sipmask.
If you don't mind I have another question. When comparing feature vectors you seem to compute their dot product, this line
I don't really see how this measures their similarity however, as a feature vector with large values would score higher than a more similar feature vector with lower values, could you maybe explain?
from sipmask.
The dot product is used to compute the feature similarity. L638-L643 select the best match.
from sipmask.
Okay, thank you very much for your time!
from sipmask.
Related Issues (20)
- How to visualize the results? HOT 3
- crop_split_cuda? HOT 1
- 关于SipMask-VIS的预训练模型 HOT 4
- CUDA error: device-side assert triggered HOT 2
- About the testing process
- SP module implementation location
- SipMask-VIS mAP is not stable HOT 2
- python setup.py develop ERROR HOT 2
- How do I set my custom label map? HOT 3
- Licensing issue
- Annotation format for a huge Dataset
- how to measure the fps? HOT 1
- AttributeError: 'float' object has no attribute 'detach' HOT 1
- 您好!我把网络改了一点点之后,训练是收敛的,但是为什么精度都是0呢?
- forward() takes from 3 to 4 positional arguments but 5 were given
- What is the problem : crop_split_cuda_backward(): incompatible function arguments.
- Hello, sorry to bother you. I wonder if you are still maintaining this code. I would like to ask what gt_pids, gt_INds and idx_GT stand for in anchor_head of SIPmask_VIS
- only size-1 arrays can be converted to python scalars HOT 2
- Implementation of SipMaskv2 in the TPAMI paper
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 sipmask.