Comments (1)
Sorry for the late reply.
I think the main reason is that in the old version we almost do not use data augmentation in the training phase while in the new version we use the commonly used data augmentation approaches.
Therefore, in the old version, when we freeze the BN parameters, the overfitting issue will be alleviated to some extent.
In the new version, when we use rich data augmentation, the effect of freezing the BN parameter is very weak.
Thanks.
from dn4.
Related Issues (20)
- CUB HOT 3
- 可视化
- batch_size只能设为1? HOT 1
- about ablation study HOT 1
- Experiment results HOT 2
- a question about ablation study HOT 6
- The results are different from the paper on miniImagenet dataset HOT 28
- About BN parameters HOT 3
- why you used --ravi HOT 3
- Some questions about resnet HOT 6
- what about multiGPU training? HOT 5
- The result of benchmark models on CUB dataset HOT 3
- Testing in a single image
- Does this DN4 network contains a pre-triaing stage? HOT 7
- About preprocessing on Stanford_Cars HOT 2
- Question on paper figure HOT 2
- Inference on one image only HOT 1
- 代码报错 HOT 1
- 细粒度数据集准确率 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 dn4.