Comments (4)
Hello @nhussein,
Thank you for your interest in our work.
Were you able to use the model weights for zero-shot inference?
In any case, I will prepare a python notebook with the necessary steps to perform zero-shot tasks using our pipeline.
from concept-based-interpretability-vlm.
I loaded the weights for the trained layers and I passed the results from zero-shot Clip to the layers. However, I did not get the same results as the one in baseline obtained from embeddings.
Thank you for the prompt response, will check out the notebook when itβs up.
from concept-based-interpretability-vlm.
I loaded the weights for the trained layers and I passed the results from zero-shot Clip to the layers. However, I did not get the same results as the one in baseline obtained from embeddings. Thank you for the prompt response, will check out the notebook when itβs up.
Hi @nhussein,
I've just uploaded the python notebook for zero-shot inference. You can find it here.
In order to reproduce the results of the paper, you should follow the steps described in the README file.
Thank you.
from concept-based-interpretability-vlm.
Thank you!
from concept-based-interpretability-vlm.
Related Issues (2)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from concept-based-interpretability-vlm.