Comments (4)
Hey! Probably you get different results due to a different batch size...
This setting is particularly challenging due to the non-i.i.d. data, so probably decreasing the BS hampers the performances.
from mib.
Hey! Probably you get different results due to a different batch size... This setting is particularly challenging due to the non-i.i.d. data, so probably decreasing the BS hampers the performances.
Thank you for the reply.
Because of my GPU memory, my batch size has a limit.
So could you recommend other hyperparameters(ex. learning rate, weight decay) for the low batch size to follow the paper's result?
from mib.
I actually never tried with a lower batch size. The main issue is using a low batch size in the 15-1 increasing the non i.i.d.-ness of data (you may try to use Batch Renormalization in place of BN as in my https://arxiv.org/abs/2012.01415, but it may alter - in positive - the results).
As a rule of thumb, you may double the iteration and halve the learning rate but I won't guarantee it will work.
from mib.
I actually never tried with a lower batch size. The main issue is using a low batch size in the 15-1 increasing the non i.i.d.-ness of data (you may try to use Batch Renormalization in place of BN as in my https://arxiv.org/abs/2012.01415, but it may alter - in positive - the results).
As a rule of thumb, you may double the iteration and halve the learning rate but I won't guarantee it will work.
Thank you for sharing~!
I will try with your recommendation.
from mib.
Related Issues (20)
- Questions about the VOC 15-1 Disjoint and Overlapped results with MiB? HOT 21
- About reproducing "Disjoint 15-5s" setting HOT 26
- question about paper:disjoint and overlapped HOT 4
- Question about init_balanced: why "-log(N+1)" operation is need in bias initialization? HOT 4
- I want to ask a question, how to load the pre-training model, please tell me, thank you very much HOT 4
- Difference in the mean IoU on test dataset HOT 1
- ADE-split.ipynb question HOT 4
- About running command related issues HOT 4
- The division of the test data set. HOT 6
- i want to use standard BN HOT 2
- about dataset
- Inconsistent 15-5s VOC results with the reported ones HOT 3
- Can not implement run.py HOT 1
- Project dependencies may have API risk issues
- visualize on the Val set (ADE20K)
- Confused about data augmentation HOT 1
- Question about how to install inplace-abn HOT 9
- code of paper scene parsing with point-based distance metric learning HOT 1
- Question of validation result in step1, 15-5s HOT 3
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 mib.