Comments (2)
Thanks for you attention.
The most important hyper-parameters I usually tune are learning rate, weight decay, and training epochs.
I only drop learning rate once time and an extra drop usually shows no help.
As Adam is not very sensitive to the initial learning rate, I usually choose the biggest working one (the loss does not explode).
More training epochs sometime helps when the initial learning is slightly small.
Hope the above helps.
from poolnet.
感谢您的关注。
我通常会调整的最重要的超参数是学习速度,体重减轻和训练时期。
我只降低一次学习率,而额外的下降通常无济于事。
由于亚当对最初的学习速度不是很敏感,因此我通常选择最大的学习方式(损失不会爆炸)。
当最初的学习量很小时,有时会有更多的训练时间会有所帮助。
希望以上内容对您有所帮助。
Thanks for you attention.
The most important hyper-parameters I usually tune are learning rate, weight decay, and training epochs.
I only drop learning rate once time and an extra drop usually shows no help.
As Adam is not very sensitive to the initial learning rate, I usually choose the biggest working one (the loss does not explode).
More training epochs sometime helps when the initial learning is slightly small.
Hope the above helps.
Thank you for your reply, which is helpful to my work
from poolnet.
Related Issues (20)
- How did you measure the accuracy, precision, recall for each dataset?
- How to create the train.lst HOT 1
- Can the model or the dataset be used commerically ? HOT 1
- Resize or not? which will be better?
- Releasing the pretrained models HOT 3
- 关于BN和model.eval()的问题 HOT 2
- detach during salient mode HOT 3
- about composite images HOT 1
- Issue in reusing the pretrained models HOT 2
- Compression network HOT 2
- About self.net.train() HOT 1
- how do you get the edge-map in DUTS-TR?
- Keras version HOT 1
- Questions about joint training HOT 2
- Question about Pre-trained model
- 关于VGG16作为backbone训练的问题
- About pretrained model using MobileNetV2 HOT 2
- Got an error when I test the pretrained model. HOT 1
- IEEE TPAMI, 2021.PoolNet+ 代码能够提供下吗?谢谢 HOT 5
- cv2.error: OpenCV(4.7.0) :-1: error: (-5:Bad argument) in function 'resize'
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 poolnet.