🧠 CNN Image Classification Project

Complete PyTorch implementation for training CNN models on custom datasets.

📁 Project Structure

cnn_image_classifier/
├── dataset/           # Your image dataset
│   ├── Human/
│   ├── Animal/
│   └── Non_Living/
├── models/            # Saved models
├── results/           # Training plots
├── config.py          # Configuration
├── train.py           # Training script
├── predict.py         # Inference script
└── README.md

🚀 Quick Start

1. Install Dependencies

pip install -r requirements.txt

2. Prepare Dataset

Organize images in folders:

dataset/
├── Class1/
│   ├── img1.jpg
│   ├── img2.jpg
├── Class2/
    ├── img1.jpg

3. Configure

Edit config.py:

NUM_CLASSES = 3
BATCH_SIZE = 32
NUM_EPOCHS = 25

4. Train

python train.py

5. Predict

python predict.py --image test.jpg

✨ Features

• Transfer Learning (VGG16, AlexNet, ResNet50)
• Data Augmentation
• Automatic Checkpointing
• Training Visualization

📊 Results

Check esults/training_history.png for training metrics.

---

⭐ Good luck with your project!