Zero-shot image classification using CLIP and Streamlit
Project description
CLIP Streamlit
A Streamlit application for zero-shot image classification using OpenAI's CLIP model.
Features
- Zero-shot image classification
- Interactive web interface
- Support for custom labels
- Confidence threshold adjustment
- Visual results with bar charts
Installation
Simple installation:
pip install clip-streamlit
The package will automatically install CLIP when you first run the application.
Usage
Run the application:
clip-streamlit
The first time you run it, it will install CLIP if needed.
Or use it in your Python code:
from clip_streamlit import run_app
run_app()
Requirements
- Python 3.7+
- Streamlit
- PyTorch
- CLIP
- Pillow
License
MIT License
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file clip_streamlit-1.0.0.tar.gz.
File metadata
- Download URL: clip_streamlit-1.0.0.tar.gz
- Upload date:
- Size: 5.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3bfe0f7436caeb2726ebf75a6ec9d0ec75ba8bde932886e3c86076d51b7f543c
|
|
| MD5 |
e124fa238e46ebd06a7b63950c9c86a9
|
|
| BLAKE2b-256 |
1698f85a095150d5b9d5a9c730104a68d6f936f0dbda42460fc0b2be80458da2
|
File details
Details for the file clip_streamlit-1.0.0-py3-none-any.whl.
File metadata
- Download URL: clip_streamlit-1.0.0-py3-none-any.whl
- Upload date:
- Size: 6.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8e825d3ad2acf233125cfeadd7e27a8fab54a29f1452f173fe3e283e7a35d695
|
|
| MD5 |
e28f0c46ded279a9ac121f3f97dae975
|
|
| BLAKE2b-256 |
36b2b4101b7b677df58d78729965efd1b579938322e4aa6679167e711e8ec704
|
