Comments (3)
Also, why do you only do spatial transformer on xy dimensions, but not on xyz dimensions?
from superpoint_graph.
Hi,
the biais is trainable, as a parameter of the proj layer (doc on pytorch). We add the identity matrix afterwards, which amounts to the same thing as https://github.com/charlesq34/pointnet/blob/d64d2398e55b24f69e95ecb549ff7d4581ffc21e/models/transform_nets.py#L47
Projections are initialized at zero because we want to initialize the transform at identity.
We only transform on xy because we don't want the network to change the vertical orientation of superpoints. A wall and a ceiling have the same shape, barring their vertical orientation. Of course the network could learn not to rotate on z if need be, but we save parameters with this insight.
However, feel free to experiment with initilialization and feature transform and report potential improvements!
from superpoint_graph.
I see. Thank you very much for your quick reply!
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
- How to control the number of superpoints in a room? HOT 6
- 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.