https://github.com/sourasishbasu/digit-classifier
Simple ML app using Gradio and Tensorflow to identify handwritten digits
https://github.com/sourasishbasu/digit-classifier
gradio mnist mnist-handwriting-recognition python tensorflow
Last synced: 3 months ago
JSON representation
Simple ML app using Gradio and Tensorflow to identify handwritten digits
- Host: GitHub
- URL: https://github.com/sourasishbasu/digit-classifier
- Owner: SourasishBasu
- Created: 2023-09-17T19:44:03.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-09-17T20:39:45.000Z (almost 3 years ago)
- Last Synced: 2025-01-09T10:39:37.937Z (over 1 year ago)
- Topics: gradio, mnist, mnist-handwriting-recognition, python, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 108 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Digit-Classifier
Interactive ML webapp using Gradio and Tensorflow to identify handwritten digits using a model trained on the MNIST dataset.
## Prerequisites:
- Python 3.9 & up
- Open Command prompt and type:
```bash
pip install gradio --user
pip install tensorflow --user
```
### To run in terminal:
- Open Powershell in the local repository folder
- Type:
```bash
python main.py
```
- The web interface will be available at the url generated: http://localhost:7860
## Using Google Colab
- The program is also available in Google Colab which can be accessed [here](https://colab.research.google.com/github/SourasishBasu/Digit-Classifier/blob/main/Digit_Classifier.ipynb).
- Copy the notebook to your Google Drive and follow the instructions to run the code.
## Usage
- Draw different digits using mouse cursor onto the sketch area and click submit.
- A list of guesses along with how confident the trained model is for other guesses will be provided with varying percentages.
- Click clear to refresh the sketch area and start drawing again.
## Images
Interface
Example