Comments (7)
@icoz69 When I was training your model on tieredimagenet, I encountered some problems. I train as follows. First, train the pretrain model according to the default parameters you give. Then use the default parameters to train the meta stage. We only got 68.30 acc on validation. We adjusted the learning rate lr from 0.0005 to 0.0001 according to the suggestions you gave. The model achieved the highest accuracy rate of 68.25 acc in the first epoch. In order to eliminate the influence of the pretrain stage, we used the pretrain model you gave when training the meta stage, but still only got 68.04acc. Can you give me detailed training strategies so that I can reproduce your results?
from deepemd.
hello, you can use the default hyper-parameters to train all datasets, but you may change it a little bit to get the best performance, though they are close. My training practice is to only tune the learning rate at the meta-learning stage. For example, if you find the validation acc saturates very quickly, then you can try a small lr.
from deepemd.
hi, when we were training the model on other datasets,
we only adjust step_size and gamma during pre-training, and lr during meta-training.
so, you may try other configurations during pre-training, such as step_size=20, while gamma=0.3. since the number of training images varies for different datasets, the optimal lr schedule may also vary.
from deepemd.
@icoz69 Thank you for your reply. If I initialize with the pretrain model you gave, how much should the lr of the meta stage be set on tierdimagenet?
from deepemd.
the provided pretrain models are not necessarily the optimal ones. i train these models using the released codes. so, you may try different values. my practice is that if the val acc stop increasing very early, I set a lower lr.
from deepemd.
@icoz69 Thanks for your advice. I used your default parameters. During the training of the meta stage, although the val acc was only 68.30, the test acc reached 71 in the final test stage. Your code is very robust, thanks for your excellent work!
from deepemd.
you're welcome. good luck to your project!
from deepemd.
Related Issues (20)
- Unable to REPEAT previous results. HOT 1
- About the effect of meta-train HOT 2
- CUB dataset is not original one HOT 1
- Code for Visualization of Fig 6 & 7 in the paper HOT 2
- Reproduction of the results of tiered-imagenet HOT 1
- hyperparameters for pre-training on TieredImageNet? HOT 1
- retun statement in the encode function of class DeepEMD
- training hyperparameters for CUB and CIFAR
- About the acc on miniImageNet HOT 2
- Fail to reproduce accuracy for miniimagenet HOT 1
- About sfc_lr in eval.py HOT 1
- dataset structure? HOT 1
- The memory of QPTH-solver(5way-1shot) is about 22GB HOT 1
- Pretrain model overfitting HOT 1
- Question on how to use this for inference HOT 1
- Can't achieve the accuracy in the papar HOT 5
- All the results are lower than paper with the default settings and feature pyramid 5,2,1 HOT 1
- Why repeat data_shot HOT 2
- MiniImageNet Dataset and TieredImageNet Dataset HOT 2
- I'm trying to reproduce under a framework named LibFewShot HOT 2
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 deepemd.