https://github.com/khushi130404/catnet
CatNet is a simple machine learning project that classifies images as either a cat or not a cat using logistic regression. The dataset consists of labeled images of cats and non-cats, preprocessed and used to train a binary classification model.
https://github.com/khushi130404/catnet
h5py matplotlib numpy pillow scipy
Last synced: 3 months ago
JSON representation
CatNet is a simple machine learning project that classifies images as either a cat or not a cat using logistic regression. The dataset consists of labeled images of cats and non-cats, preprocessed and used to train a binary classification model.
- Host: GitHub
- URL: https://github.com/khushi130404/catnet
- Owner: Khushi130404
- Created: 2024-07-07T02:43:11.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-02-12T03:39:02.000Z (3 months ago)
- Last Synced: 2025-02-12T04:32:39.479Z (3 months ago)
- Topics: h5py, matplotlib, numpy, pillow, scipy
- Language: Jupyter Notebook
- Homepage:
- Size: 2.81 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🐱 CatNet - Cat Image Classifier
CatNet is a simple machine learning project that classifies images as either a cat or not a cat using logistic regression. The dataset consists of labeled images of cats and non-cats, preprocessed and used to train a binary classification model.
## 📌 Features
- Loads and preprocesses the dataset (resizing, normalizing, and flattening images)
- Implements Logistic Regression from scratch
- Includes training, optimization, and prediction functions
- Provides test evaluations on new images
## 📂 Dataset Information
- 209 training images (64x64 RGB images)
- 50 test images (64x64 RGB images)
- Labels: 1 for cat, 0 for non-cat
## 💻 Tech Stack
- Python: Primary programming language
- NumPy: For numerical computations
- Matplotlib: For data visualization
- PIL (Pillow): For image handling
- SciPy: For scientific computing
- h5py: For handling dataset storage in HDF5 format
## 📊 Model Performance
- Achieves high accuracy in detecting cats using a basic logistic regression approach.
- You can improve the model by implementing deep learning using neural networks (e.g., TensorFlow/Keras).
## 🎯 Future Enhancements
- Implementing deep learning with a convolutional neural network (CNN)
- Expanding dataset for better generalization
- Integrating deployment via Flask or FastAPI