Comments (4)
They are the same as the computation overhead introduced by the point-based is not that significant. The overhead can also be observed in this figure actually (there is a small shift in the x-axis between MinkowskiNet and SPVCNN).
from spvnas.
Thanks for the response. I see, indeed, I can also see the small shift!
-
Based on Haotien's response here: #19, I got the impression that voxelization/devoxelization procedure in SPVCNN will have some impact on MACs and GPU latency when compared to MinkowskiNet at the same
cr
? (B/c the sparse convolution branches are exactly the same in both nets.) Am I correct in my understanding that the penalty for voxelization/devoxelization procedure actually does not penalize the model's inference time much, esp. at smallcr
? -
This raises another Q. to me: at the same
cr
, e.g.cr=1.0
, shouldn't the number of trainable parameters in MinkowskiNet be lower than the corresponding SPVCNN? (B/c SPVCNN uses point transformation MLPs whereas MinkowskiNet does not.) However, in the pre-trained models you released, both models seem to be equal in number of parameters; am I missing something?
from spvnas.
- I think your understanding is correct. The voxelization and devoxelization will indeed introduce some overhead. However, as we are doing them once per several layers, the overhead can be amortized.
- You are right. From https://github.com/mit-han-lab/e3d/blob/master/spvnas/core/models/semantic_kitti/minkunet.py#L149-L165, you may see that we have also defined the point transforms for MinkowskiNet although we are not actually using them. We will remove them to resolve the confusion.
from spvnas.
I see, that clarifies it. Thanks!
from spvnas.
Related Issues (20)
- nuScenes lidarseg evaluation on EvalAI fails without returning any error
- When will the nuscenes configs be released?
- Question on devoxelization HOT 2
- Ask for help about iou per class
- Testing Pretrained Models fail HOT 2
- How to calculate the Madds of SPVCNN? HOT 1
- Model configs is not available HOT 2
- non-negative coords only? HOT 1
- evaluate.py running out of memory because there is no no_grad modifier
- couldn't find methods, modules , functions etc HOT 6
- visualize.py has bugs HOT 2
- Could you release the code of 3d object detection on KITTI dataset ? HOT 1
- CUDA error: invalid configuration argument HOT 3
- Data Preprocessing HOT 2
- reproduce result low HOT 2
- Trained model on nuscenes availability HOT 1
- A lightweight Cylinder3D model with much higher performance is now available!!! HOT 3
- About training on other datasets HOT 1
- nuScenes training pipeline HOT 1
- Can't use pretrained models HOT 4
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 spvnas.