Comments (6)
You have to do it yourself, what i do is extract the features and make an l2 distance between them. If the distance is under a threshold i considered that is the same person.
from deep-person-reid.
Thank you
from deep-person-reid.
Hi,
@msalexms, enjoying this topic for a couple of questions I have.
I have written a script using Yolov5 for the person detection. I extract the features using the reid model/weights. Then do a cosine similarity using Torchreid. I also tried L2 following your comment. I tried multiple weights from Zoo. Same domain, mixed domain...
Similarity detected for someone completely different is very close from a real reid.
I tried from a fixed camera in an entrance (phone video). Images are extracted. 1 person enter and must be reid. Another one enter and they are both on the image. The first one left the image, only the second one is present.
Any idea that could lead me to a successful path?
from deep-person-reid.
To let know, got better result by implementing the reranking.
Anything I could add more in case of?
I am now adding a comparison of multiple weights for the same model.
from deep-person-reid.
Related Issues (20)
- Output Shapes of Model During Training and Evaluation Differs HOT 1
- Missing packages when trying to export models to ONNX from Docker container HOT 1
- can you write code for LSTM models ?? HOT 1
- can you tell me , why i am getting this kind of erros
- Error: all query identities do not appear in gallery
- torchreid
- Columns and DataType Not Explicitly Set on line 44 of export.py
- Train for non-person Re-Identification?
- URL link in this project is not available
- Using the cosine similarity between embeddings generated by OsNET-Ain doesn't provide good results, HELP !! HOT 1
- Training error,CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm
- pretrained weights for "osnet_ain_x1_0" are broken
- 求助 How to export .pth files in model_zoo to onnx files?
- 对多个类别做reid, 是否可以放在一起训练
- 关于reid模型转rknn HOT 1
- list index out of range
- mAP using osnet_x1_0 and resnet50 is weird HOT 2
- How to fine-tune a model with a custom dataset? HOT 1
- How to run in production
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 deep-person-reid.