Mudassir-08/alexnet-cifar10-demo

AlexNet for CIFAR-10 Classification (PyTorch Research Implementation)

Overview

This project implements a modified AlexNet architecture for CIFAR-10 image classification using PyTorch.

The model classifies images into 10 categories: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck

Implementation Includes:

• —Modular PyTorch architecture
• —Custom training pipeline
• —Early stopping mechanism
• —Evaluation metrics (accuracy, confusion matrix)
• —Deployment-ready inference system

Key Highlights

• —Peak Validation Accuracy: 89.48%
• —Test Accuracy: 88.63%
• —Early stopping: Epoch 46/90
• —Strong convergence and stable training
• —Good generalization with minimal overfitting

Model Architecture

Input: 3 × 64 × 64 image

Conv → BatchNorm → ReLU → MaxPool Conv → BatchNorm → ReLU → MaxPool Conv → BatchNorm → ReLU Conv → BatchNorm → ReLU Conv → BatchNorm → ReLU → MaxPool

AdaptiveAvgPool (4×4)

Flatten

FC → ReLU → Dropout FC → ReLU → Dropout FC → Output (10 classes)

Dataset

• —CIFAR-10 dataset
• —60,000 images total
• —50,000 training
• —10,000 test
• —10 classes

Training Configuration

• —Framework: PyTorch
• —Optimizer: SGD (momentum=0.9)
• —Learning Rate: 0.1
• —Scheduler: ReduceLROnPlateau
• —Batch Size: 256
• —Epochs: 90 (early stopped at 46)
• —Loss: CrossEntropyLoss

Training Behavior

• —Fast convergence in early epochs
• —Stable improvement until ~epoch 30
• —Plateau around 88–89%
• —Early stopping triggered

Results

Inference Pipeline

Image → Resize → Normalize → Model → Softmax → Prediction

Model Checkpoint

File: alexnet_cifar10.pth

Contains:

• —modelstatedict
• —optimizerstatedict
• —num_classes

Deployment

• —Hugging Face Spaces
• —Gradio Interface
• —Real-time inference ready

Project Structure

AlexNet/

├── data/

├── notebooks/

├── src/

├── savedtrainedmodel/

├── main.py

├── README.md

├── requirements.txt

└── .gitignore

Author

Malik Muhammad Mudassir Iqbal

Mudassir-08 Deep Learning Researcher

License

Apache-2.0 License