Comments (1)
you can see the article“https://arxiv.org/pdf/1703.05175.pdf”,
Section 2.6,it said:
Episode composition A straightforward way to construct episodes, used in Vinyals et al. [29] and
Ravi and Larochelle [22], is to choose Nc classes and NS support points per class in order to match
the expected situation at test-time. That is, if we expect at test-time to perform 5-way classification
and 1-shot learning, then training episodes could be comprised of Nc = 5, NS = 1. We have found,
however, that it can be extremely beneficial to train with a higher Nc, or “way”, than will be used
at test-time. In our experiments, we tune the training Nc on a held-out validation set. Another
consideration is whether to match NS, or “shot”, at train and test-time. For prototypical networks,
we found that it is usually best to train and test with the same “shot” number.
I also don't understand the principle。。
from few-shot.
Related Issues (20)
- Why did you choose 200 epochs instead of 300, 600 or more?
- Queries about the MAML implementation HOT 2
- How train with a new dataset HOT 5
- How can I test single image use my trained model(5way3hot,protonet)?Any help is appreciated! HOT 1
- EvaluateFewShot in MAML
- KeyError: 'class_name' HOT 4
- Result question HOT 3
- About ProtoNet's accuracy on miniImageNet
- BUG: model CANNOT be shared in a derived class HOT 1
- ModuleNotFoundError: No moudle named 'config'
- Metrics about ProtoNet's accuracy HOT 2
- mini-imagenet access HOT 3
- ImportError: cannot import name 'Feature' from 'setuptools' HOT 1
- How to use pytest to predict the test code in the tests directory and display the running result. HOT 3
- experiments are completed, next? did i get the result of the model? nothing!
- Why using dummy data to calculate loss and update the meta model in MAML?
- How to use pytest to predict the test code in the tests directory and display the running result? HOT 1
- question of class MatchingNetwork code
- few_shot.utils is not found
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 few-shot.