/Simpsons-Character-Image-Recognition

Simpsons Character Image Recognition using Tensorflow

Primary LanguageJupyter Notebook

Simpsons Character Image Recognition using Tensorflow

Python Framework Data

Simpsons Face Recognision web app can predict 43 different kind of Simpsons Faces with 93% overall validation accuracy.

Upcomming Features for this WebApp:

  • Multilebel classification system for images
  • Multiple classification system for vedios
  • More pleasant looking UI and many more...

Check out the live demo: Comming Soon(After Project Completion)

Vedio demo:

GIF

Note

Use this URL - Click Me - in case if you are faccing any problem with th WebApp or source code.

Source Code: github link

How to run the project?

  1. Clone or download this repository to your local machine.
  2. Install all the libraries mentioned in the requirements.txt file with the command pip3 install -r requirements.txt
  3. Download the Pre-Trainned Model from the Given Link Below. And paste it in the modelfolder in the project home directory.
  4. Open your terminal/command prompt from your project directory and run the file app.py by executing the command streamlit run app.py.
  5. You will be automatically redirected the your localhost in brower where you can see you WebApp in live.

Architecture of your Project Home Directory

IMG-folder_directory

Source to the Pre-trained Modles

Click here to download the Pretrained model for this classification whaich has arround 93% val_accuracy.

you can also check my Kaggle page to see how i have obtained this accuracy and you can manupulate the code as your need.