Comments (6)
Which chapter are you referring to?
from imgcomp-cvpr.
The data used for plotting the rate-distortion curve is given in the plotter.py file.
Could I know if these data was obtained by training the model at different configs, and how can we get these different configs or all the pre-trained model at different configs? Thanks in advance!
from imgcomp-cvpr.
Ah I see. The figure and the table were obtained by training 7 different models for different operating points (see paper, "To obtain models for different bitrates, we adapt the target bitrate t and the number of channels K"). We released 3 of these models. But the plotting ocde (plotter.py
can in theory take any combination of models and dataset.
from imgcomp-cvpr.
But there are 28 pair of (bpp, MS-SSIM) data used in plotter.py, how can we get these datas from only 7 different models?
from imgcomp-cvpr.
The curve is using the interpolation code in plotter.py Line 111. Did you train the models?
from imgcomp-cvpr.
I read the code in plotter.py and plotted the curve successfully! Thanks a lot!
from imgcomp-cvpr.
Related Issues (20)
- The size of your trained model HOT 2
- compressed images are large HOT 11
- why only mask the last channel? HOT 1
- Testing monochromatic images on your code HOT 6
- about soft_quantize sigma parameter
- bpp comparison HOT 3
- test error HOT 2
- inference error HOT 4
- log_dir_root HOT 4
- training
- CodecDistance HOT 4
- python version
- train stop at"-STARTING TRAINING-------------" HOT 8
- inference using real_bpp HOT 2
- about soft and hard quantization HOT 2
- How to optimize with mse? HOT 1
- Question about 'distortion_to_minimize' HOT 3
- Download link/ pretrained models HOT 2
- which time we can get torch ?
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 imgcomp-cvpr.