Comments (6)
Can you upload your implementation ?
from fewshotwithoutforgetting.
I just modified code from here https://github.com/apache/incubator-mxnet/tree/master/example/image-classification. I only change the network architecture to 4 conv blocks.
from fewshotwithoutforgetting.
@dremaker52 I am also trying to re-implement the network. Could you tell me how did you implement the 2nd training procedure? (the novel weight generator)
from fewshotwithoutforgetting.
Hi all, I just uploaded the implementation code.
from fewshotwithoutforgetting.
@gidariss Thanks for the update. How many epoch you have trained to get the numbers reported in README? I just tried 60 epoch for both stage 1 and 2 of training and only got 50.3% of the novel classes for 5-way 1-shot miniImageNet dataset. (Conv128)
from fewshotwithoutforgetting.
In all Mini-Imagenet experiments both training stages last for 60 training epochs. However, because the training split of Mini-Imagenet is relatively small and there is a danger of overfitting, the training snapshot (i.e., the model parameters at the end of each training epoch) that "survive" from each training stage is that that achieves the highest accuracy on the novel categories of the validation split of Mini-Imagenet. In other words, there is early stopping strategy in order to avoid overfitting.
So, for the model with the Conv128 feature extractor, at the 1st training stage the training snapshot that is kept at the end is that of the 25th training epoch and at the 2nd training stage the training snapshot that is kept at the end is that of the 35th training epoch. This actually means that for the Covn128 case many of the 60 training epochs are actually useless and can be avoided.
from fewshotwithoutforgetting.
Related Issues (20)
- Can you share some details on how to generate the miniImageNet pickle files, I want to test on my own datasets, many thanks. HOT 5
- Obtained test accuracy lower than reported for miniImageNet HOT 1
- ask for environment details
- Test the model on own dataset.
- Could you please give me some advices for improving acc_both? HOT 5
- A question about the training process
- The dataset HOT 3
- question of data_train_opt
- Training issue und
- Training issue with Pytorch1.1, python2.7
- UnicodeDecodeError when training HOT 8
- ValueError: The provided metric AccuracyNovel for keeping the best model is not computed by the evaluation routine. HOT 4
- Bias in the Classifier Class HOT 1
- fixed branch
- Reminder: installation tips HOT 1
- Dynamic Few-Shot Visual Learning without Forgetting
- the code problem in your paper : how to get weight_base
- Question on whether the process of feature extraction has used the pretrained model on ImageNetFS
- Can you tell me how to get accuracyboth and accuracybase? After running the code, I only get accuracynovel_ CNF
- The first stage training report an error
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 fewshotwithoutforgetting.