gender classification with dataset added

[ombajrangpurohit]

Description

This Pull Request adds a complete machine learning project for Gender Classification using a Convolutional Neural Network (CNN) built with TensorFlow/Keras.

Following the repository's guidelines for interactive and educational data science content, this project is submitted as a self-contained Jupyter Notebook (.ipynb) alongside a detailed descriptive markdown layout.

Category

• Machine Learning
• Image Classification

Model Architecture & Pipeline Details

The implementation follows a classic deep learning architecture optimized for binary image classification:

1. Data Preprocessing: Input image rescaling (1./255) and normalization utilizing standard image dimensions of 150x150x3.
2. Feature Extraction Layers: Three staggered 2D Convolutional layers (Conv2D with 32, 64, and 128 filters respectively running ReLU activations) interleaved with MaxPooling2D reduction layers.
3. Classification Head: Flattened feature vector fed into a Dense hidden layer of 512 units, culminating in a single-neuron output layer running a Sigmoid activation function for binary classification (Male/Female).
4. Optimization: Compiled using the Adam optimizer and tracked via binary_crossentropy loss.

What is Included?

• Gender Class.ipynb: The core interactive pipeline notebook containing imports, network architecture definition, compilation metrics, training logs, and an inference prediction helper function.
• Detailed inline commentary explaining the purpose of each sequential block for student review.

Checklist

• My code follows the style guidelines of this repository.
• I have performed a self-review of my own code.
• My modifications do not disrupt any existing files or folders in the machine_learning/ path.