Comments (3)
(a) For prototypical networks, we set meta-training shot == meta-test shot for all datasets. In other words, if you want to test your model on 1-shot scenario, you need to set meta-training shot to be 1.
(b) From what I remember, label smoothing was only applied for miniImageNet.
from metaoptnet.
Thanks for your response @kjunelee
I understand that the shots are matched, my question was more on the number of ways. The original protonet paper found that increasing ways improved their performance. So I was wondering if you do the same in your re-implementation with Resnet-12 or do you train only with 5-way. Also, have you tried experiments with increasing ways for the SVM and RR models?
from metaoptnet.
Sorry I misread your question.
From what I remember, in our implementation increasing ways did not help for Prototypical Networks. Hence, we always trained on 5-way for experiments in our paper. Note that we use different hyperparameters (e.g. number of query samples) from original ProtoNet paper and this may be the reason why we did not observe a gain by increasing "way". To be honest, we didn't try much on increasing the number of ways as it increases memory consumption. It might be still useful to try it. One caveat is that due to the way we implemented multi-class SVM, the running time will blow up if you try >10-way. Our ridge regression implementation does not have such problem.
from metaoptnet.
Related Issues (20)
- Some questions about MetaOptNetHead_Ridge HOT 2
- About accuracy in CIFAR_FS 5-way 5-shot and how to implement MetaOptNet-SVM-trainval HOT 2
- Keep-rate scheduling of DropBlock in a multi-GPU environment HOT 2
- Why the accuracy of the Prototypical Network is higher than the reported version in paper? HOT 1
- Where is the parameter gamma HOT 1
- Does the performance of different SVM heads vary largely? HOT 1
- question about "--episodes-per-batch" HOT 2
- Meta gradient Computation HOT 3
- About"TypeError: btrisolve() takes 3 positional arguments but 4 were given"
- what is the difference between novel categories and base category? HOT 1
- Question about meta-validation and meta-testing HOT 4
- Parameters for ProtoNet using ResNet12 as backbone
- the parameters config for the cifarfs,the accuracy is only 63% HOT 1
- could you tell me the link which about the miniImageNet_category_split_train_phase_train.pickle ?
- Thanks and some questions
- Overlapping between meta-training classes and meta-testing classes HOT 1
- How do I know what the real category of tieredImagenet is? HOT 1
- Pretrained model
- Project dependencies may have API risk issues
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 metaoptnet.