Comments (2)
The training in the initial stage is not stable and may harm the model performance. We use the auxiliary training to solve the problem and decay the weight of the auxiliary training loss for later epochs.
from crossdomainfewshot.
Why does this auxiliary training help stabilize the training? The loss may let your model fit the val dataset and give worse acc for test dataset.
from crossdomainfewshot.
Related Issues (20)
- question about fast weight
- can the model be trained with multiple GPUs
- About the training time
- Cannot get CUB_200_2011 dataset from "python3 process.py cub" HOT 3
- GG! best accuracy 0.000000 in Feature encoder pre-training stage HOT 2
- baseline
- Feature encoder pre-training
- Expected object of scalar type Float but got scalar type Double for argument #2 'mat1' in call to _th_addmm
- Where is the code of nms? I can't find it.....help
- How to get the T-SNE effect in the paper HOT 1
- Question about model training. HOT 2
- Question about Training w/ learning-to-learned feature-wise transformations.
- Documentation on Plantae Dataset Version (iNat 2018) HOT 1
- cars_train not found HOT 2
- code error in dataset py HOT 4
- Ask about the use of some codes
- Problems were encountered with partitioning the places365 dataset HOT 1
- more detail explanation for "create_graph=True" and "weight.fast" HOT 1
- when Training with multiple seen domains
- Plantae Dataset NOT Available? HOT 3
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 crossdomainfewshot.