Comments (1)
Hi @anonymoussss Yes, using a single teacher of senet154 will lead to worse results than the current teacher ensemble, but we did not test the scenario if the single teacher is stronger than the teacher ensemble.
from meal-v2.
Related Issues (20)
- Paper Inconsistency with Code HOT 2
- why not use temperature in distillation loss? HOT 1
- what's the training result on imagenet when training from scratch ? HOT 9
- datasets HOT 2
- What is the performance of the teacher model HOT 2
- 使用mobilenet_v2的预训练参数,top1的精度从0开始,请问这正常嘛? HOT 2
- 疑问 HOT 1
- can not download model HOT 2
- MEAL-V2和MEAL-V1的区别 HOT 1
- why are top1 and top5 both 0.0? HOT 2
- other databases for training HOT 1
- torch.nn.DataParallel error HOT 5
- img size, why 380? HOT 1
- torch.nn.DataParallel error HOT 2
- can't export to onnx model HOT 1
- Could not find the generator loss. HOT 2
- loss Value HOT 1
- Does this method change the probability of the class? HOT 3
- Discriminator LR Decay HOT 5
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 meal-v2.