Comments (6)
You are right. Here the output form is consistent with the KITTI label files (KITTI rectified camera coordinate ). Please refer to the introduction of KITTI training labels for details.
from pointrcnn.
OK thanks for your answer ! Another point, is there a way to disable the calibration step easily to train PointRCNN on other annotated point clouds ?
from pointrcnn.
You need to check the codes manually to update the codes where the calibrations are used. Most of them are in the dataset related codes, maybe you should write a new dataloader for your own point clouds.
from pointrcnn.
I will write a new dataloader, it will be more appropriate I think. Another point, why are you subsampling the point cloud into 16,384 points as mentioned in the paper? Is it only for a memory point of view ?
from pointrcnn.
The PointNet++ needs a fixed number of input points and then I subsample 16384 points as the input.
from pointrcnn.
this post has helped to clarify my doubts too. thanks.
from pointrcnn.
Related Issues (20)
- compile iou3d on windows10 HOT 1
- segfault when generating gt
- ImportError: No module named torch.utils.cpp_extension HOT 1
- nvvm
- Checkpoint model shape mismatch HOT 1
- what should I do when I train and eval in offline GT augmentation mode?
- No module named 'pointnet2_cuda' HOT 1
- Compile iou3d error HOT 3
- What't the function of 'images' in training model using PointRCNN? HOT 1
- optional:plane HOT 1
- RuntimeError with customized loss while running loss.backward() HOT 2
- Use the point cloud frame generated by Carla for prediction and training
- Problem with installation
- implement pointrcnn on Windows? HOT 4
- Problem in third step when doing build and install file HOT 1
- While training
- About RPN Output Results
- code stuck at epoch 0 do not through any error
- RuntimeError: CUDA out of memory
- eval_rcnn.py problem ValueError: too many values to unpack (expected 2) HOT 2
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 pointrcnn.