Comments (6)
Up! I also wonder how to adjust the number of superpoints in the method.
Thanks.
from superpoint_graph.
You can simply change --reg_strength
: higher values will yield fewer superpoints.
With supervised partitions, you have more options:
--CP_cutoff determine the minimum size of a Superpoint
--spatial_emb determines the weight of the spatial extent of superpoints : high value -> superpoint mostly determined by position, low value: mostly by geometry/color.
from superpoint_graph.
@loicland : Thanks for your reply :)
The --CP_cutoff
and --spatial_emb
are understandable to me. For reg_strength
, could you elaborate more on how this value can impact the number of superpoints? I know, in this code, it will be used in the cut-pursuit
algorithm. But I still don't know intuitively how this hyperparameter will impact to the superpoints number in the cut-pursuit
algorithm. Thanks!
from superpoint_graph.
Cut pursuit approximates a signal on a graph with simple (short) contour. To do so, we penalize a fidelity loss with the weight of the cut between constant component multiplied by reg_strength
. To simplify, this reg_strength
expresses how much approximation error is allowed per unit of contour (cut edges). In our case, since the graph signal approximated is a set of geometric/radiometric features , it rules the tradeoff between the simplicity of their geometry and the length of their shapes.
Small reg_strength
: the contour penalty is not very important, will yield many small superpoint with very simple geometry.
Large reg_strength
: the contour penalty dominates, will yield few superpoint with very simple contours but potentially complex geometry.
In practice, the relationship between reg_strength
and the number of superpoints is complicated and depends on many things (point density, sensor precision, what kind of shapes you are using, etc.). The easiest way would be to try a few values on a sample scene until the smallest objects of interest are in their own superpoint.
from superpoint_graph.
@loicland Thank you for your reply.
I have read the ssp papar and found the regularization strength definition(Supplementary Material A.1) in the GPMP equation, thank you for your explanation again. But I am still confusing about how the --spatial_emb
can influence the number of superpoints? In my understanding the supervised LPE generate the main feature for cut pursuit algorithm.
from superpoint_graph.
Hi!
We are releasing a new version of SuperPoint Graph called SuperPoint Transformer (SPT).
https://github.com/drprojects/superpoint_transformer
It is better in any way:
✨ SPT in numbers ✨ |
---|
📊 SOTA results: 76.0 mIoU S3DIS 6-Fold, 63.5 mIoU on KITTI-360 Val, 79.6 mIoU on DALES |
🦋 212k parameters only! |
⚡ Trains on S3DIS in 3h on 1 GPU |
⚡ Preprocessing is x7 faster than SPG! |
🚀 Easy install (no more boost!) |
If you are interested in lightweight, high-performance 3D deep learning, you should check it out. In the meantime, we will finally retire SPG and stop maintaining this repo.
from superpoint_graph.
Related Issues (20)
- Inconsistent class_maps for s3dis HOT 2
- CUDA error when training for Semantic3D HOT 1
- the version of metrics HOT 2
- When making ply_c, fatal error: numpy/ndarrayobject.h: No such file or directory HOT 3
- Segmentation fault (core dumped) HOT 2
- Running on Stanford3dDataset_v1.2_Aligned_Version, the error occurs. HOT 6
- CMake error HOT 1
- Which version of Pytorch is needed for this code? HOT 1
- ModuleNotFoundError: No module named 'torchnet' HOT 3
- RuntimeError: scan failed to synchronize: an illegal memory access was encountered HOT 2
- L0-cut pursuit partition algorithm HOT 3
- cupy_backends.cuda.api.driver.CUDADriverError: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered HOT 3
- About the number of superpoints HOT 2
- Overfitting soon after around 30 epochs HOT 13
- How to visualize SSP HOT 1
- ValueError: need at least one array to concatenate HOT 1
- Pretrained weight link
- How to visualize SSP results? HOT 1
- What parts of the code should be changed in the custom dataset when using this network? 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 superpoint_graph.