Comments (5)
Hi, for semantic segmentation, the sparsity constraint is implemented at:
(1) different (disjoint) sub-parts,
CEN/semantic_segmentation/main.py
Lines 396 to 400 in 158e313
(2) adding the loss of the sparsity constraint,
CEN/semantic_segmentation/main.py
Lines 282 to 283 in 158e313
For image-to-image translation, the sparsity constraint is implemented at:
(1) different (disjoint) sub-parts,
CEN/image2image_translation/main.py
Lines 112 to 119 in 158e313
(2) adding the loss of the sparsity constraint,
CEN/image2image_translation/main.py
Lines 208 to 213 in 158e313
from cen.
Thank you for your reply! However I am still confused as to where the sparsity constraint in terms of channel exchanging is implemented, as the sections of code you referenced seem to be applying the sparsity constraint to the loss calculation.
I am mainly confused about
CEN/semantic_segmentation/models/modules.py
Lines 12 to 15 in 158e313
which seems to exchange channels within all of
x[0]
and x[1]
, instead of disjoint sub-parts of them.from cen.
Hi, take semantic segmentation as an example:
We apply the sparsity constraints on disjoint sub-parts of BN scaling factors in,
CEN/semantic_segmentation/main.py
Lines 396 to 400 in 158e313
In the case of two modalities, we divide channels into two disjoint sub-parts, which is implemented by adding
param[:len(param) // 2
and param[len(param) // 2:]
to slim_params. Followed up by the sparsity loss on slim_params, which means only the sub-parts in slim_params are constrained by L1.
We find if a channel is out of the sparsity constraints (L1), its BN scaling factor can be hardly lower than the small threshold during training. Therefore we check the criteria for channel exchanging directly on the whole channels,
CEN/semantic_segmentation/models/modules.py
Lines 12 to 15 in 158e313
Since constraining half (disjoint sub-parts) of the channels is already implemented in
main.py
, checking the exchanging criteria on the whole channels is almost equivalent to disjoint sub-parts.from cen.
That makes sense. Thank you for your detailed explanation!
from cen.
@yikaiw 你好 (1) 我不是特别理解用L1norm来惩罚 scale factor 在loss function 的意义,这一项在loss function里不就是让 scale factor 越来越小么 简单的来说。能不能稍微解释一下呢, 谢谢🙏
(2)这里的certain portion 就是disjoint 的那部分的意思是么?
from cen.
Related Issues (17)
- Paper request HOT 2
- Query regarding applicability to other tasks HOT 2
- Formatting iOS Lidar Depth Data For Transfer-Learning HOT 2
- Question about CEN HOT 6
- Non colorised masks HOT 1
- How can get the datasets of "train" and "val" HOT 4
- 为什么对rgb, depth和ens的loss求和? HOT 1
- In the end of CE HOT 9
- 关于多模态的形式 HOT 1
- About visualization figures in paper HOT 7
- About where the mean(ensemble) is calculated HOT 5
- Some question about the image size HOT 2
- 最终表示的问题 HOT 4
- For fusion of 3 modalities HOT 4
- some question for image size HOT 6
- Method to choose a good lambda (in Equation 4) 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 cen.