Comments (4)
I test this algorithm on a single faster rcnn and get a worse performance than nms.
So, I posit, the algorithm has certain limitations
from weighted-boxes-fusion.
Just to be sure about performance on single model, I made an experiment.
I took RetinaNet based on ResNet152 backbone which was trained on Open Images dataset. Then I cut final NMS layer. With this model I predicted TOP 500 raw boxes based on confidence for each validation image. Then I calculated metric mAP(0.5):
- No NMS (Raw boxes) – mAP: 0.171762 – value is small because of large amount of intersected boxes at the same object.
- With NMS and default THR - mAP: 0.490199 IOU THR: 0.5
- With NMS and best THR - mAP: 0.490588 IOU THR: 0.47
- With WBF and optimal parameters (grid search): mAP: 0.453182 IOU THR: 0.43 Skip box THR: 0.21
So, for this case WBF is worse than NMS for single model. Probably WBF (in current implementation) is bad for case of large amount of boxes with poor prediction quality.
from weighted-boxes-fusion.
I didn't have chance to check it. All my models had NMS block at the end. I still have plans to make some related experiments.
from weighted-boxes-fusion.
@ZFTurbo I am using YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x models with WBF for object detection in VisDrone2019 dataset. It seems like the confidence scores increase when used with WBF but the number of prediction decreases.
I would like to know how can I calculate or perform evaluation of the ensemble model predictions in terms of mAP, precision, recall? Is there any bultin function provided in the WBF repository to perform the ensemble model evaluation?
I appreciate your help.
Regards,
Bijay
from weighted-boxes-fusion.
Related Issues (20)
- Incorrect conf_type='max' mode HOT 1
- Strange result if boxes are intersected inside one model HOT 2
- confidence score > 1 issue HOT 1
- Bbox is 'Nan' when weights have 0 HOT 4
- How to find the optimal hyper-parameters in the ensembling process HOT 6
- Can work with polygon object ? HOT 1
- Compatibility for Instance Segmentation HOT 1
- Building wheel for llvmlite ... error HOT 1
- How to use in Yolov5
- Implemetation on mobile phone HOT 4
- label list on SSD HOT 1
- run NMS on empty bounding box from one of ensembled models HOT 5
- Single instance NMS
- 2d bbox wbf compute result error
- Is WBF consider to be part of Ensemble Learning HOT 4
- Back propagation when multiple models are ensembled
- model fusion for rotating boxes
- Recall and Confusion matrix, also the confusion matrix, of the WBF HOT 5
- about map_boxes in run_benchmark_oid.py HOT 2
- AttributeError: module 'numpy' has no attribute 'str'
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 weighted-boxes-fusion.