Comments (5)
So let's go over the generalized sparse convolution quickly https://stanfordvl.github.io/MinkowskiEngine/generalized_sparse_conv.html#id2
For all latex code define inside $$, use http://mathb.in/ to render them online.
The input coordinates and output coordinates can be defined arbitrarily as
-
By default, it uses the same input coordinates for output
$\mathcal{C}^\text{out} = \mathcal{C}^\text{in}$ . -
As I mentioned, I would not go that route. If you need, I would simply use
.dense()
function to convert the sparse tensor to a dense one and do convolution after you decrease the resolution of the space significantly. However, if you absolutely need that, I can make a cleaner API function.
from minkowskiengine.
Thanks for your quick reply.
I was using the terminology of sparse conv and submanifold conv in Submanifold Sparse Convolutional Networks. I just want to make sure I can use your library to reproduce other network.
I appreciate your generalized framework. The current API looks quit flexible to me. There's no need to include such expensive operator here.
from minkowskiengine.
@chrischoy Hi, Thanks for your code.
I feel that the MinkowskiConvolutionTranspose(generate_new_coords=True) is equivalent to the Dense Convolution regardless of the negative coordinates of the output. Am I correct?
from minkowskiengine.
No it is not equivalent. The input and output are both sparse tensors. How could it be equivalent?
from minkowskiengine.
@chrischoy Thanks for your reply.
I mean that in your implement, the input coordinates and output coordinates are the same. But for regular convolution, the out_coords_key includes in_coords_key's neighborhood.
As you have mentioned, in your experiments, expanding the output coordinate space will harm the performance, but I want to try this in my tasks where the input is very sparse.
I found that it seems the MinkowskiConvolutionTranspose(generate_new_coords=True) can achieve this function, i.e., the regular convolution, because the output coordinates of the transpose convolution are expanded. Am I correct?
from minkowskiengine.
Related Issues (20)
- How can I get the index of downsample points?
- Error when calling MinkowskiPooling HOT 2
- Sampling from VAE's latent space HOT 1
- MinkowskiEngine/src/gpu.cu(104): warning: function "minkowski::format_size" was declared but never referenced
- RuntimeError: Error compiling objects for extension HOT 1
- Invalid automatic min_coordinate calculation for SparseTensor.dense
- MinkowskiEngine building wheels HOT 2
- Failed to install the latest MinkowskiEngine (Dec 2023) HOT 3
- Minkownski Convolution with stride 2 and Kernel Size 4
- GPU memory leak when runing multiplication
- Clarification on SparseTensor representation of pointcloud coordinates.
- About Running Issues on NVIDIA RTX 4090 Graphics Card HOT 3
- gradient backward question
- Program terminated when trying to get a kernel_map
- pip uninstall minkowskiengine won't work for me HOT 2
- How can I do matrix multiplication based on MinkowskiEngine?
- Coordinate arrangement sequence
- ERROR: Could not build wheels for MinkowskiEngine, which is required to install pyproject.toml-based projects HOT 2
- return_maps_only arg in sparse_quantize HOT 2
- Failed to install the latest MinkowskiEngine
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 minkowskiengine.