Comments (4)
The feature extractor is frozen, and they re-train a linear classifier from scratch for each testing episode.
If you take a look at methods/baselinefinetune.py
and methods/meta_template.py
, you could see they re-initialize a linear layer for a set_forward_adaptation
call in each test episode, which means the fine-tuned weight is independent between different test episode.
CloserLookFewShot/methods/meta_template.py
Line 102 in e03aca8
from closerlookfewshot.
Thank you for your reply. So in each episode, it only use support set to fine-tune the linear layer and use query set to test. I guess the main reason to fine-tune and test in the unit of episode is to keep consistent with mete-testing stage for fair comparison.
But I think if use the whole support set for all episodes in test dataset to fine-tune(and not only the classifier but also the backbone) and use the whole query set for all episodes in test dataset to evaluation for baseline and baseline++ model, which means fine-tune in the traditional way, it may get higher accuracy. And if further use the validation dataset to fine-tune the baseline and baseline++ model, to meta-training the meta-learning model, it may further improve accuracy.
Hoping for your opinion!
from closerlookfewshot.
The purpose of sampling different episode is to evaluate the performance under few-shot learning scenario. For example, to evaluate 3-way 5-shot tasks, we want to know the performance when the training data (of target task) only contain 3 classes and 5 examples per class. Thus, there is no reason to use examples other than the support set of an episode to finetune the model in most cases.
from closerlookfewshot.
OK, I understand. Thank your for your explanation.
from closerlookfewshot.
Related Issues (20)
- Training accuracies are low and their gaps are big when Conv4 backbone is used.
- Question on feature_loader.py:32,33
- The stop_epoch number of maml
- Larger batch size for CUBS.
- Query Regarding Figure 5.
- TypeError: super() argument 1 must be type, not classobj
- assert params.num_classes >= 1597, 'class number need to be larger than max label id in base class' HOT 5
- h
- Training using 'protonet', 'matchingnet', 'relationnet', 'relationnet_softmax', 'maml', 'maml_approx' methods with an unbalanced dataset.
- Baseline++ cross_char accuracy lower than Baseline
- About the lacking of query sample in data_loader and the lacking of target in calculating loss
- h
- CUB dataset's link no longer valid
- Baseline ++ validation wrongly reported in paper?
- What does fid mean in write_miniImagenet_filelist.py ?
- How to fine-tune the Matching Network HOT 1
- errro _pickle.PicklingError HOT 1
- RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'
- how to make the experiments repeatable?
- How to get the pre-trained model?
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 closerlookfewshot.