Comments (3)
Have you solved this problem?
from pams.
Have you solved this problem?
To get the model of similar performance with the paper, I trained the model with 300 epochs & decay at 150 epochs. (a bit strange since the paper reports only training for 30 epochs). But maybe this will help.
from pams.
thanks
from pams.
Related Issues (16)
- Something wrong about the pretrained models HOT 3
- Training Error HOT 1
- seems nothing output after running test HOT 6
- something wrong ahout 4bit_rdn_x4.pt HOT 1
- Some confusion in quant_ops.py HOT 2
- Something confusion about the testing
- Testing error HOT 2
- Something confused in quant_ops.py HOT 2
- How to calculate model size claimed in paper HOT 1
- Unable to load 4bit_rdn_x4.pt
- train problem
- code doesn't match the paper HOT 1
- 复现精度 HOT 6
- How to calculate the ssim claimed in the paper? HOT 1
- 模型量化后,训练时间变长,推理速度变慢
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 pams.