Comments (1)
The reasons of using deconv are 2-fold:
1. Less params.
1.1 Take an example that the feature vector is size 1024, and we want to reconstruct 1024 points.
- FC: Assume that the number of neurons are non-increasing. The first layer is at least 1024 -> 31024 (each point has x,y,z coordinates). That is param amount: 102431024. In the following layers, the number of params will be 3102431024.
- deconv: the first layer, the convolution param amount: 102433*1024. But in the following layers, the number of params are decreasing.
- This effect is more obvious if we are reconstructing 5000 points. Each layer of FC takes at least 350003*5000, which is huge. But for deconv, the we have similar number of params as in the case of reconstructing 1024 points.
- That is, deconv is much more scalable.
- Of course, we don't have to assume that the number of neurons are non-increasing for FC. In this case, the number of params depends on how to implement FC/deconv. It is meaning less to make absolute comparison.
- Deconv has better performance
- In experiments, reconstructing large number points with FC will result in disappointing performance.
- In real objects / scenes, each point is not totally independent to another point. Hence it is not necessary to use FC. Deconv is more suitable.
from so-net.
Related Issues (20)
- How to test the model on SHREC2016 retrieval challenge? HOT 4
- Compile ‘index_max’ fail. HOT 12
- Sampling code non-uniform? HOT 4
- Retrieval result unclear HOT 3
- Question about point cloud transformation HOT 2
- index_max builds but fails at runtime HOT 1
- Error in SO-NET code HOT 12
- Supplementary material HOT 2
- How about the Training Time?
- Data augmentation not work? HOT 1
- The function of index_max. HOT 4
- How to train the model on SHREC2016
- Very low mIoU on part set HOT 1
- The error in ‘Application - Part Segmentation’ HOT 2
- How to get the input of the autoencoder?
- Low validation mIoU despite high validation accuracy on part seg HOT 1
- test file for autoencoder HOT 1
- Error in "python setup.py install" HOT 1
- can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
- how to install the index_max? HOT 1
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 so-net.