Comments (6)
Hi, the main differences arise from the changes in evaluation.
In the paper, we adopt the coco-format ground truth and use COCO scripts for evaluation.
However, since PR 36, we introduce the usage of Bitmask. Now, the evaluation runs on predictions and ground truth with the Bitmask format.
These two formats have obvious differences. For the coco format, the predictions of different instances can overlap. However, using our bitmask format, one pixel only belongs to one instance.
Currently, we have mmdet-pretrained MaskRCNNs to be published. MaskRCNN with ResNet50, trained with a 1x schedule, can achieve 16.8 in AP.
from bdd100k.
Thanks for your detailed explanation.
I adopt the coco-format ground truth for training and evaluation, which is converted from bitmask format by the official script. The Mask R-CNN with ResNet50 and 1x schedule reaches AP = 19.8. It would be great if your training code could be published.
from bdd100k.
from bdd100k.
I see. Is there any script to generate coco format from polygons? Or did you convert the format with something like poly2patch
function in link and then to rle with cocoapi
?
from bdd100k.
Yes. In scalabel, we provide this one: https://doc.scalabel.ai/label.html#to-coco.
However, we don't advise our users to do so. Because our official evaluation adopts the bitmask format.
from bdd100k.
Thanks a lot.
from bdd100k.
Related Issues (20)
- Unable to download 100k images HOT 1
- Semantic Segmentation JSON File has images with labels of categories which are listed under Panoptic Segmentation!
- Questions about calculation of mAP
- whereis removed area? I cannot find them
- annotation don't match images
- BDD100K Object Detection on EvalAI submission FileNotFoundError HOT 6
- MOT format to BDD100k format HOT 1
- EvalAI status stuck on "Runnung" HOT 3
- labels of validation set
- MOT2020 source offline; downloads dead slow when it was online HOT 2
- `to_coco_panseg`: leads to OOB `IndexError`
- No module named 'numpy' HOT 1
- Corresponding images for segmentation masks HOT 1
- BDD-X
- EvalAI status stuck on "Runnung"(CVPR2023 MOT)
- conversion of train labels to coco format hangs
- float pixels for bounding boxes? x1 y1 x2 y2
- Eval.run insane memory usage HOT 1
- Multiprocessing Error HOT 3
- converting labels to mask problem HOT 1
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 bdd100k.