Comments (5)
Yeah, I agree that it would be best if we were able to use the VOC version of mAP for PASCAL VOC, but I'm not well versed in the differences so I wouldn't be able to implement that.
Out of curiosity, what's the difference in mAP that you observe? If it's not a huge difference, then I think it's fine. And TIDE is meant as a way to find places you can improve your model, not necessarily to replace the official evaluation numbers. So as long as the numbers correlate, there shouldn't be any issue.
from tide.
Well, I got a ~10% higher mAP with PASCAL VOC metric than COCO metric on VOC2007 test. Some people say that PASCAL VOC greedily finds best match (using IoU criteria) for current pred box and if it is already matched it marks the current pred box as false. While in COCO the search continues if the current best match already matched.
Anyways, I agree with you that the role of TIDE is to find how one can improve the OD model, regardless of ways of evaluating mAP. After all, COCO metric is a reasonable metric.
from tide.
Well, I got a ~10% higher mAP with PASCAL VOC metric than COCO metric on VOC2007 test. Some people say that PASCAL VOC greedily finds best match (using IoU criteria) for current pred box and if it is already matched it marks the current pred box as false. While in COCO the search continues if the current best match already matched.
Anyways, I agree with you that the role of TIDE is to find how one can improve the OD model, regardless of ways of evaluating mAP. After all, COCO metric is a reasonable metric.
Hi,@machengcheng2016, could you share the code to convert pascal detection results to coco json style? My conversion get a much lower mAP in tide than mmdetection.
from tide.
Details of my conversion are in this issue
from tide.
I've solved it.
from tide.
Related Issues (20)
- Comparing Across Scale HOT 4
- Custom dataset evaluation HOT 1
- Feature Request: Compress masks as they are added to Data
- Feature Request: Finish statically typing the API HOT 1
- "score" parameter in Data.add_detection is annotated as "int", should probably be "float"
- list input can be bounding box (Nx4) or RLEs ([RLE]) HOT 1
- Crashes with a DivideByZeroError when there are no detections HOT 3
- Even when using the ground truth values as predicted values, there is error. HOT 1
- code of Comparison of Scales HOT 1
- Getting bbox AP @ 50: 0.00 HOT 1
- How to handle images with no ground truth box
- About My dataset HOT 1
- where dataset defines
- Keypoint Evaluation
- Is there any sample code how to evaluate the detections at different scales and classes? Is there a sample how to use the Qualifier class?
- Use case where no segmentation field is present in a COCO file and where COCO result file contains all information about the dataset
- Can I use TIDE on my own dataset - given coco-formatted Ground-Truth and predicted Bounding Boxes? HOT 2
- My Coco files contain no segmentations - only bounding boxes. Why is this incompatible? HOT 1
- The sum of mAP is not 100 HOT 3
- Test Custom Trained Yolov7 Model
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 tide.