hxdengberkeley / pointcnn.pytorch Goto Github PK
View Code? Open in Web Editor NEWA PyTorch implemetation of PointCNN (CS294-131 Course Proj)
License: MIT License
A PyTorch implemetation of PointCNN (CS294-131 Course Proj)
License: MIT License
PointCNN.Pytorch/utils/util_funcs.py
Line 53 in 6ec6c29
The final size is known to begin with. May be faster to init to torch.zeros with the proper size
Hi, how can i train part-segmentation model, i don't see this model in your code .
Thanks for the great implementation! I notice training is quite slow. Any pointers on what part of the code can be optimized for speed?
this code can't run in ubuntu.
Line 179 in 6ec6c29
In this place ,I think shuffling point clouds should be ahead of sampling point clouds .
line 179 should exchange the place with 180.
Is that right?
PointCNN.Pytorch/utils/util_funcs.py
Line 57 in 6ec6c29
It's unhealthy to define a variable "n" inside a loop that uses "n" as it's enumerator
(how does this even work?)
Thanks so much for your works! I try to reproduce the results of PointCNN in Pytorch but still cannot get a reasonable result and I find your project just now. But I have some question about the code you provided.
The network in this repository is some kind of different from the origin one.
1, the author uses three depthwise conv layer to produce the transform matrix X. You just use one depthwise layer plus another two dense layer. It will need more parameters compared to the original and maybe arise overfitting.
2, why do you remove batchnorm in your dense layer? I think this is unreasonable.
3, the configuration is quite different from the original one
in the original code, the output channel has a coefficient 3. And it seems that you use 5 xconv layers while the author uses 4.
4, what's the best accuracy you get on ModelNet40?
Nevertheless, thanks for your sharing. Hope my questions are not too much.
Hi, is this repo complete?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.