erictuanle / goingdeeperwpointnetworks Goto Github PK
View Code? Open in Web Editor NEWThis project releases the code for the Paper "Going Deeper with Point Networks"
This project releases the code for the Paper "Going Deeper with Point Networks"
Hi, I have noticed in your PartNet dataset that you load a key 'label_cat' from the h5 files for PartNet. I don't see such a field in the original h5 files provided by PartNet (there is only 'label_seg'). I am using PartNet v0 from the official ShapeNet website. Which version of PartNet do you use and where one can get it? Thank you in advance!
Test issue.
Hi, @erictuanle ,
The training / testing script for PartNet dataset is missing. Could you upload it? Or could you list the steps on modifying the ShapeNet training / testing script for dealing with PartNet dataset?
Thanks~
Hi, @erictuanle ,
Thanks for releasing the package. When I run the test script:
python test_shapenetpart.py --network deepConvPN --workers 4 --batch_size 4
I got the following error (the model with trained weights is missing)
FileNotFoundError: [Errno 2] No such file or directory: 'models/training_deepconvpn_shapenetpart_params.pth'
Would you help to release your trained models?
THX!
As shown in Table 1 and Table 5 in your paper, the mIoU of PointNet++ and DGCNN in ShapeNetPart is 82.9% and 79.8%.
However, both of measurements reported in the dgcnn paper is 85.1%.
What cause the difference of results reported in the two paper?
Hi, how to download the "category_per_class.txt" of shapenet dataset.
Anyone know? Thank you
Hi, I've read the paper and I am confused with section 3.2 and section 3.3. Could you please answer the following two questions?
In section 3.2, you proposed Multi-resolution processing to substitute multi-scale version originally proposed in PointNet++. However, Multi-resolution approach was proposed in PointNet++ which was also more efficient than MSG. Have you compared memory efficiency with it? Moreover, why down sampling approach you proposed is better than multi-resolution approach in PointNet++?
In section 3.3, algorithm 2, line 2, function BackwardMaxPooling gets gradient of max pooling wrt output gradient. But in conventional implementation, backward of maxpooling needs to know input data, output data and output gradient so that output data can be compare with input data and input gradient can be updated according to them. But input data of in MaxPooling is freed in forward pass stage. Thus, how can we get back propagation of Max-pooling operator without knowing its input whose memory is freed in forward pass stage?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.