Skip to content

Dog Vision: A web app that uses deep learning to identify dog breeds from uploaded images. Predicts breed with confidence score and provides Google search link for more information. User-friendly tool for dog breed identification and exploration.

License

Notifications You must be signed in to change notification settings

RushikeshKothawade07/Dog_Vision

Repository files navigation

Dog_Vision

Dog Vision is a web application that uses deep learning to identify dog breeds from uploaded images. It provides a user-friendly interface for users to explore and discover the breed of their dogs with ease.

Key Features

  • Breed Identification: Upload an image of a dog and let Dog Vision predict the breed with high accuracy.
  • Confidence Score: Get a confidence score associated with each predicted breed, indicating the model's level of certainty.
  • Google Search Integration: Explore more about the predicted breed by directly accessing a Google search page for images and information.
  • Multiple Image Support: Analyze multiple dog images in one go and get breed predictions for each image.
  • Visual Appeal: Enjoy a visually appealing and intuitive user interface for a seamless user experience.

Dog Vision Web App Shots :

Screenshot 1 Caption: UI for Dog Vision streamlit web app

Screenshot 2 Caption: Uploading an image and obtaining breed prediction

Screenshot 3 Caption: Displaying the predicted breed with confidence score and google search integration

Usage

  1. Clone the repository:

    git clone https://github.com/YourUsername/Dog_Vision.git
  2. Run the app:

 streamlit run app.py

Enjoy using Dog Vision and have fun exploring the world of dog breeds!

About

Dog Vision: A web app that uses deep learning to identify dog breeds from uploaded images. Predicts breed with confidence score and provides Google search link for more information. User-friendly tool for dog breed identification and exploration.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published