dynamicml 1.1.5

A lightweight binary image classification system built with scikit‑learn, focusing on k‑Nearest Neighbors (kNN) and classical ML models. It features dynamic, model‑aware image preprocessing (HOG, scaling, PCA) that adapts automatically to image characteristics, enabling efficient training and reliable inference for custom datasets.

DynamicML 🚀

Dynamic, model‑aware classical machine learning for image classification

CREATED BY SUNKARA SAI GANESH , KARROTHU MOURYA , KUDIRELLA SANMUKA SAI, DONTALA. KIRAN KUMAR.

DynamicML is a lightweight Python library built on top of scikit‑learn, Tensorflow and Pytorch that enables classification using classical machine learning models and advanced deep learning models, with a strong focus on dynamic, model‑aware preprocessing. The library is designed to automatically adapt preprocessing pipelines based on data characteristics and model requirements, making it easy to experiment, benchmark, and deploy classical ML solutions for image data. Typically in just 2-4 lines of code.

---

DynamicML – (Classical ML) Project Overview

This project implements classical machine learning models supported by DynamicML, built on top of scikit-learn.

Classical ML classifier (Single model at a time)

The goal is to classify images into two or more than two classes efficiently using lightweight ML models.

Supported Models (DynamicML)

DynamicML supports most classical classifiers from scikit-learn, including:

🔹 Linear Models

SGDClassifier

RidgeClassifier

🔹 Distance-Based Models

k-Nearest Neighbors (kNN)

Radius Neighbors

Nearest Centroid

🔹 Support Vector Machines

Linear SVM

Kernel SVM (RBF, Polynomial, Sigmoid)

🔹 Probabilistic Models

Gaussian Naive Bayes

Multinomial Naive Bayes

Complement Naive Bayes

Bernoulli Naive Bayes

🔹 Tree-Based Models

Decision Tree

Random Forest

Extra Trees

🔹 Boosting & Ensembles

AdaBoost

Gradient Boosting

HistGradientBoosting

Bagging

Voting

Stacking

🔹 Neural & Advanced Models

MLPClassifier

GaussianProcessClassifier

⚠️ Note: In this project, only one model is trained at a time for binary classification.

Dataset Structure dataset/ │ ├── class_0/ │ ├── img1.jpg │ ├── img2.jpg │ └── ... │ └── class_1/ | ├── img1.jpg | ├── img2.jpg | └── ... │ └── class_2/ ├── img1.jpg ├── img2.jpg └── ...

Each folder represents one class.

Preprocessing Pipeline

The project uses a classical ML pipeline for data processing:

📊 Train-Test Split train_test_split( test_size=0.2, stratify=y, random_state=42 )

80% Training

20% Testing

Stratified to maintain class balance

⚙️ Model Training

Example (Random Forest):

RandomForestClassifier( n_estimators=100, max_depth=None, random_state=42 )

Steps:

Load dataset

Train model

Evaluate performance

Save model using joblib

📈 Evaluation Metrics

The model is evaluated using:

✅ Accuracy

✅ Classification Report

✅ Confusion Matrix

Example output:

Accuracy: 0.91

Precision | Recall | F1-score ... 💾 Model Saving

Trained models are saved as:

modelname_timestamp.joblib

Saved bundle includes:

{ "model": trained_model, "label_encoder": label_encoder }

This ensures reproducibility and easy deployment.

🚀 How to Run Step 1: Install Requirements pip install scikit-learn numpy opencv-python scikit-image joblib Step 2: Run Training Scikit_Img_Classif_Supervised.RandomForest_Classifier("dataset_path") 🏗 System Architecture Dataset ↓ Preprocessing ↓ Classifier (Single Model) ↓ Evaluation ↓ Model Saving

🎯 Why Classical ML Instead of CNN?

Lightweight

Faster training

Works well on small datasets

Suitable for hackathons

Easier interpretability