This project involves training and evaluating two machine learning models on different data sources for image classification. The goal is to compare their performance and assess their effectiveness in a specific task.
-
Data Source Model01: Trained using Data :The dataset we used is called MNIST. This is a large collection of hand-drawn digits 0 to 9 and is a good dataset to learn image classification on as it requires little to no preprocessing..
-
Data Source Model02: Trained using prepared Data from Kaggle.
- Model01: 0.9000
- Model02: 0.9629761904761904
- 0.96257
Model02, trained on Data Source 2, achieved a higher accuracy and better leaderboard score compared to Model01, indicating its superior performance in this image classification task.
To replicate or extend this project, ensure you have the necessary dependencies installed and follow the provided scripts for training and evaluation.
- Clone the repository:
- git clone (https://github.com/whoami01001/DigitRec) - cd (https://github.com/whoami01001/DigitRec) - Install the required dependencies listed in `requirements.txt`. - Run the training scripts to train the models. - Evaluate the models using the provided evaluation scripts. - For further details or questions, please refer to the documentation or open an issue in the repository.