Comments (6)
The default parameters should do that. train/train_cls.py will train an MSG model on modelnet40.
from pointnet2_pytorch.
This repo matches the performance from the paper. If I recall correctly, the only hyper-parameter you need to change is the number of points (to 10k) for that.
from pointnet2_pytorch.
@erikwijmans Thanks for your reply! My training results do match the paper, but it is still 0.x% accuracy gap with the paper. And I find that, in your implementation, the architecture seems to be pruned.
self.SA_modules.append(
PointnetSAModuleMSG(
npoint=512,
radii=[0.1, 0.2, 0.4],
nsamples=[32, 64, 128],
`mlps=[[input_channels, 64], [input_channels, 128],`
################### in the paper, it seem to be a three layer mlp for per sub-pointnet
[input_channels, 128]],
use_xyz=use_xyz
)
)
I want to know if you do this on purpose?
Thanks!
from pointnet2_pytorch.
I have played around with the architectures a fair amount. Makes sense to change them back to the ones given in Charles' repo, I will make that change.
from pointnet2_pytorch.
@erikwijmans How to test the model for modelnet40? Could you give some tips to re-implement the experiment result in the paper?
from pointnet2_pytorch.
@erikwijmans Thanks for your reply! My training results do match the paper, but it is still 0.x% accuracy gap with the paper. And I find that, in your implementation, the architecture seems to be pruned.
self.SA_modules.append( PointnetSAModuleMSG( npoint=512, radii=[0.1, 0.2, 0.4], nsamples=[32, 64, 128], `mlps=[[input_channels, 64], [input_channels, 128],` ################### in the paper, it seem to be a three layer mlp for per sub-pointnet [input_channels, 128]], use_xyz=use_xyz ) )
I want to know if you do this on purpose?
Thanks!
Hi, sorry to bother. Did you match the paper's accuracy with the newest arch? I run the code and only got 0.9023 with the default hyper-parameters.
from pointnet2_pytorch.
Related Issues (20)
- device = torch.device('cuda')在paddlepaddle上应该是怎样的
- How can the prediction result be restored to the original size?
- FP module bug when know is None HOT 1
- Is there some way to make the SA_module and FP_module deterministic HOT 1
- How to build with CUDA9.0 ? HOT 4
- Inference using my own point cloud on S3DIS dataset using PointNet++
- integrate with Lightning ecosystem CI
- pointnet2_ops_lib: Compilation Error HOT 8
- grouping_operation function not expected result
- Unauthenticated git no longer supported HOT 1
- ball_query.cpp error:cpu not support HOT 1
- @pengPeterpeng I tried running the conftest.py file but getting the following error
- A lightweight Cylinder3D model with much higher performance is now available!!!
- python setup.py build_ext --inplace HOT 3
- pointnet2_ops install problem HOT 10
- Error when importing pointnet2_utils HOT 1
- error: could not create 'pointnet2_utils\_ext.cp37-win_amd64.pyd': No such file or directory
- Modify pointnet_ops_lib successfully,but can not import new attribute
- the problems may meet and fix if have to use old "etw_pytorch_utils" version
- nvcc fatal : Unsupported gpu architecture 'compute_37'
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 pointnet2_pytorch.