How christy62/ml-project-digit-recognition works
This is a handwritten-digit classification project: its manually created image dataset represents digits 0–9 as 25×25 pixel arrays, and a PyTorch neural network is trained and evaluated on separate test data. The documented model uses a 128-neuron ReLU hidden layer and produces ten classes; evaluation includes a confusion matrix. The notebook is the only executable source shown, so internal processing stages are represented at the level supported by the README rather than inferred from unsampled code.
Main entry points: training_ml_digit_recognition.ipynb Test evaluation · images Handwritten images
Components 7
Image data
- Handwritten images
images - Separate test set
training_ml_digit_recognition.ipynb
Recognition model
- Train model
training_ml_digit_recognition.ipynb - Digit classifier
training_ml_digit_recognition.ipynb
Model evaluation
- Test evaluation
training_ml_digit_recognition.ipynb - Confusion matrix
training_ml_digit_recognition.ipynb
Other components
- Project user
Connections 6
- Project user → Handwritten images: creates
README.md - Handwritten images → Train model: provides images
README.md - Train model → Digit classifier: trains
README.md - Separate test set → Test evaluation: provides test data
README.md - Digit classifier → Test evaluation: is evaluated
README.md - Test evaluation → Confusion matrix: generates
README.md