Comments (9)
NO.
in meta-learning setting, meta-training includes training and testing, meta-test includes training and testing as well. The label space between meta-training and meta-testing is separated properly. For sub-stage, say training and testing in meta-train or meta-testing, the leakage
is normal, not an error.
from maml-pytorch.
Thank you for your response!
I am aware that the sub-stage update is achieved through fast_weights
. My question is, at the end of the forward()
function, does self.meta_optim.step()
update parameters of the base learner, i.e., the \theta in the paper?
from maml-pytorch.
Yes, the meta_optim.step() will update \theta parameters only. The updates of fast_weights will be ignored in sub-stage of test.
from maml-pytorch.
At the meta-testing phrase, we need to forward()
the meta-test tasks to evaluate the corresponding testing performance at the meta level (not the task level). More importantly, we only want to get the fast weights for those tasks, because the meta test tasks should not be used to update the meta learner, i.e., \theta. However, the \theta is also updated since self.meta_optim.step()
is always part of forward()
.
Do you think there is any need to take out self.meta_optim.step()
in meta testing?
from maml-pytorch.
In stead of self.meta_optim.step()
, shouldn't we do the following?
if training is True: self.meta_optim.step()
from maml-pytorch.
Oh, maybe u r right.
During the test, no need to optimize the \theta parameters.
U can try it and see any problems.
from maml-pytorch.
I have already tried and it turned out the optimization step is required to be left out in meta testing. Otherwise it would give overly optimistic results for be trained on meta test sets.
from maml-pytorch.
Ok, thx. Feel free to submit a PR.
from maml-pytorch.
Hi, all. Please git pull to get the latest version which solved test data leaking bugs.
from maml-pytorch.
Related Issues (20)
- Overlap between meta-training and meta-testing? HOT 1
- why use custom grad clip function?
- omniglot dataset download error HOT 1
- Does the hessian really gets computed? HOT 1
- Can you please add a 1-d CNN model to the learner.
- Incorrect losses_q HOT 3
- about dataset spiltting
- create_graph parameter is False hence first-order MAML? HOT 1
- Asking about inner and outer loop
- 您好,对于代码有两个问题,请教您一下,谢谢 HOT 3
- About training and testing HOT 6
- can you offer us your requirements of environment?
- Why is `for epoch in range(args.epoch // 10000):` HOT 2
- Why the code for Learner is so complicated? HOT 1
- 请问模型权值文件在哪里进行保存?代码在哪里? HOT 1
- debug
- Using the Learner object for my project, Loss not behaving at its best
- About accuracy HOT 6
- What is the backup file for and what is the reference navie5 in navie5?
- 准确率不变 HOT 4
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 maml-pytorch.