Comments (2)
Unfortunately I lost the original code to do this but it’s really simple to do. My ONNX files are based on CompressAI pretrained models, but you can do it on any other weights as well as long as the model structure is the same.
For factorized you just export net.g_a and g_s and that’s it. Hyperprior compression you can make a function that merges everything together and export that, for decompression export h_s and g_s separately. Then, you can manually compare the structure with my ONNX files.
You may need to tweak the model structure a bit depending on what TensorRT version you’re running, like for older versions you need to change torch.abs to condition check with torch.where because it’s not supported.
from licoris.
Thank you for your response.
from licoris.
Related Issues (1)
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 licoris.