Skip to content

Project to utilise the capabilities of Pre trained models

Notifications You must be signed in to change notification settings

Aniike-t/Style-Transfer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

31 Commits
 
 
 
 
 
 

Repository files navigation

Run Locally

Description

Leveraging advanced computer vision techniques, including the powerful VGG19 and CartoonGAN models. This project enables users to seamlessly blend the content of images/videos with the artistic style of another.

Client Side

  1. Open the terminal and navigate to the client directory:

    cd client
    cd stylerepfrontend
  2. Install Node Package Manager dependencies:

    npm install
  3. Install required packages:

    npm install axios
    npm install react-router-dom
    npm install hamburger-react
  4. Start the development server:

    npm start

Server Side

  1. In another terminal window, navigate to the server directory:

    cd server
  2. Install TensorFlow for Python by running the following command inside app.py:

    pip install flask flask_cors opencv-python-headless tensorflow tensorflow_hub numpy scipy
  3. To download the model tar file, please visit the following link: Arbitrary Image Stylization Model

    After downloading the file, extract its contents and paste them into the server\models\modelStyleTransfer folder. If there are existing files in this folder, you can replace them with the extracted files. This will ensure that the model files are available for the style transfer functionality in your server code.

  4. Start the server:

    python app.py

Outputs

  • Style Transfer:

    Style Transfer

  • Video :

    Style.Transfer.mp4