Comments (2)
hi hfutzzw:
Of course.
We first generate a paragraph for each image in COCO dataset.
Then we use zero-shot retrieval based on a conventional BERT model and frozen the parameter (without image encoder).
At last, we normalise the output of paragraph and original caption. Compute the similarity score and select the top-K samples.
from image2paragraph.
Marked as resolved for no response.
from image2paragraph.
Related Issues (20)
- install not work with python = 3.8.16 HOT 8
- Out of Memory Issue in Semantic Segmentation HOT 2
- Input type and weight type should be the same HOT 1
- Comparison with minigpt4 HOT 2
- pip install markupsafe not compatible with project source code HOT 1
- Excellent work HOT 1
- run question HOT 10
- Possible Langchain integration? HOT 1
- Comment instructions outdated HOT 2
- Data Generation
- About the visualization
- Region Semantic Models Do Not Work Well
- Colab example is broken (403 error)
- 能用 StableVicuna 换掉 chatgpt 吗
- Retrieval results with no Trainable Parameter?
- Unable to load weights from checkpoint file HOT 4
- pydantic HOT 2
- Suggestion - Integrate MobileSAM into the pipeline for lightweight and faster inference
- TypeError: issubclass() arg 1 must be a class HOT 2
- Can corresponding text descriptions be generated in batches for images in the image dataset?
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 image2paragraph.