Comments (2)
Thank you for your interest in our work. We have employed ViT and BERT from OpenAI's CLIP as feature extractors. As a result, we needed to modify the source code of CLIP, which can be seen at https://github.com/openai/CLIP/blob/main/clip/model.py
(line 235
for images, line 354
for text). You may refer to my src/tools/extract_embedding.py
for the model loading and forward process.
from lgva_videoqa.
I forgot to mention one point: please do not apply normalization to the features, as it would result in loss of information.
from lgva_videoqa.
Related Issues (9)
- Missing h5 extracted feature files HOT 2
- code reproduction problem HOT 2
- the meaning of qid in next_train_qa.json HOT 1
- the code for multi-gpu training HOT 1
- The extraction embedding coding of "bbox_features" HOT 5
- Incomplete extract_embedding.py code? HOT 1
- About CLIPβs text-encoder. HOT 3
- Processing of candidate words HOT 3
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 lgva_videoqa.