https://github.com/subhayudutta/decktracker

Decktracker is a web app that classifies and identifies the type of playing cards using Convolutional Neural Networks (CNN) and Streamlit.
https://github.com/subhayudutta/decktracker

cnn python streamli tensorflow transfer-learning

Last synced: about 2 months ago
JSON representation

Decktracker is a web app that classifies and identifies the type of playing cards using Convolutional Neural Networks (CNN) and Streamlit.

• Host: GitHub
• URL: https://github.com/subhayudutta/decktracker
• Owner: subhayudutta
• Created: 2023-06-22T05:12:42.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2023-11-10T08:14:26.000Z (over 2 years ago)
• Last Synced: 2025-10-04T22:52:21.273Z (8 months ago)
• Topics: cnn, python, streamli, tensorflow, transfer-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 3.64 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Decktracker

Decktracker is a web app that classifies and identifies the type of playing cards using Convolutional Neural Networks (CNN) and Streamlit.

## Features

- Classify and identify playing cards using CNN.

- Streamlit-powered web interface for easy interaction.

- Intuitive design for a user-friendly experience.

## Running the App Locally

### Step 1: Run the CardClassification.ipynb file

![Step 1](./venv/Screenshot_3.jpg)

### Step 2: Save the card_pred.h5 model.

![Step 2](./venv/Screenshot_2.jpg)

### Step 3: Run the streamlit app

![Step 3](./venv/Screenshot_4.jpg)

### Step 4: Upload Image and View Classification Result

![Step 4](./venv/Screenshot_5.jpg)

## Dataset

You can download the dataset from [Kaggle](https://www.kaggle.com/datasets/gpiosenka/cards-image-datasetclassification).