Comments (2)
I've tested the code with the original BDD annotations, and it works. So, the problem seems to be with my result files.
I'm following the following format from the bdd100k docs, but I'm getting the following errors. Any help is appreciated!
pydantic.error_wrappers.ValidationError: 10 validation errors for Frame
labels -> 0 -> box2d
value is not a valid dict (type=type_error.dict)
labels -> 1 -> box2d
value is not a valid dict (type=type_error.dict)
My result JSON format, according to BDD100k documentation:
- videoName: str, name of the current sequence,
- name: str, name of the current frame,
- framIndex: int, index of the current frame within the sequence,
- labels []:
- id: str, unique instance id of the prediction in the current sequence,
- category: str, name of the predicted category,
- box2d []:
- x1: float,
- y1: float,
- x2: float,
- y2: float
from bdd100k.
I've figured out the problem. In the result template, box2d should be a dictionary instead of a list. In addition, there has been a typo on the documentations. framIndex should be frameIndex!
With this, it works as expected now!
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.