Comments (3)
lzm2275965881
commented on August 16, 2024
I found that the camera extrinsics generated by CVT are different from those generated by Fiery, I'm confused, too. Do you know why now?
from cross_view_transformers.
yangxh11
commented on August 16, 2024
I found that the camera extrinsics generated by CVT are different from those generated by Fiery, I'm confused, too. Do you know why now?
Maybe it is the inverse matrix? I did not read the code of Fiery
from cross_view_transformers.
haruishi43
commented on August 16, 2024
In lyft/nuscenes-devkit#73, the code seems to indicate that KITTI doesn't use the same ego positions for camera and lidar. Maybe the authors tried to support KITTI and since the BEV GTs are generated using ego lidar poses, the authors might have tried to account for the mismatch ego poses by transforming the camera ego pose to lidar ego pose.
from cross_view_transformers.
Related Issues (20)
- error training HOT 1
- How long does it take to train the model?
- Geometric reasoning in cross-view attention
- How to train this for segmenting more than 2 classes? HOT 1
- Question about camera extrinsics
- Question about the implementation of 'camera-aware positional encoding' part
- The labels of dataset Argoverse.
- loss function mutation when training
- When run [train.py] RuntimeError: unmatched '}' in format string HOT 2
- Discrepancy in the validation IOU values for Driveable Area segmentation HOT 15
- About setting1 HOT 1
- The label link is broken
- generating labels error : [OSError]: [Error 24] Too many open files HOT 1
- train error : urllib.error.URLError : <urlopen error Error instantiating 'cross_view_transformer.model.backbones.efficientnet.EfficientNetExtractor' : <urlopen error [Errno 111] Connection refused> ]
- Error executing job with overrides HOT 1
- no test.py
- about the model test
- Error running training (LR Scheduler) HOT 1
- 运行时出现以下错误
- visualize of attention
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 cross_view_transformers.