Coder Social home page Coder Social logo

autodistill / autodistill-gpt-4v Goto Github PK

View Code? Open in Web Editor NEW
24.0 5.0 4.0 25 KB

GPT-4V(ision) module for use with Autodistill.

Home Page: https://docs.roboflow.com

License: MIT License

Makefile 10.30% Python 89.70%
autodistill computer-vision gpt-4 gpt-4v object-detection

autodistill-gpt-4v's Introduction

Autodistill GPT-4V Module

This repository contains the code supporting the GPT-4V base model for use with Autodistill.

GPT-4V, developed by OpenAI, is a multi-modal language model. With GPT-4V, you can ask questions about images in natural language. The autodistill-gpt4v module enables you to classify images using GPT-4V.

This model uses the gpt-4-vision-preview API announced by OpenAI on November 6th, 2023.

Note

Using this project will incur billing charges for API calls to the OpenAI GPT-4 Vision API. Refer to the OpenAI pricing page for more information and to calculate your expected pricing. This package makes one API call per image you want to label.

Read the full Autodistill documentation.

Read the GPT-4V Autodistill documentation.

Installation

To use GPT-4V with autodistill, you need to install the following dependency:

pip3 install autodistill-gpt-4v

Quickstart

from autodistill_gpt_4v import GPT4V

# define an ontology to map class names to our GPT-4V prompt
# the ontology dictionary has the format {caption: class}
# where caption is the prompt sent to the base model, and class is the label that will
# be saved for that caption in the generated annotations
# then, load the model
base_model = GPT4V(
    ontology=CaptionOntology(
        {
            "person": "person",
            "a forklift": "forklift"
        }
    ),
    api_key="OPENAI_API_KEY"
)
base_model.label("./context_images", extension=".jpeg")

License

This project is licensed under an MIT license.

๐Ÿ† Contributing

We love your input! Please see the core Autodistill contributing guide to get started. Thank you ๐Ÿ™ to all our contributors!

autodistill-gpt-4v's People

Contributors

capjamesg avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

autodistill-gpt-4v's Issues

Simple code has an issue

Hello,

I am trying to test the code snippet posted on the web. However, I get the following error:

Labeling ../../People/cussion-with-a-colleague-in-an-office-characteristics-of-a-determined-person.j
Traceback (most recent call last):
File "/media/M2Disk/Projects/CompVis/ObjectDetection/AutoDistill/GPT4/autodistill-gpt-4v/genlabels.py", line 10, in
base_model.label(input_folder=folder_name, output_folder='mldata')
File "/media/M2Disk/Projects/CompVis/ObjectDetection/AutoDistill/autodistillenv/lib/python3.11/site-packages/autodistill/detection/detection_base_model.py", line 52, in label
detections = self.predict(f_path)
^^^^^^^^^^^^^^^^^^^^
TypeError: GPT4V.predict() missing 1 required positional argument: 'classes'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.