Machine Learning with PyTorch and Deep Learning

This repository contains various machine learning and deep learning projects implemented using PyTorch and scikit-learn.

Repository Structure

📁 basics_pytorch

• Basic PyTorch operations and concepts
• Gradient descent implementations
• Autograd examples
• Training pipelines
• Dataset and DataLoader usage

📁 CrossEntropyLoss.py

• Cross-entropy loss implementations
• Softmax functions
• Multiclass classification examples
• Animal classifier model
• Linear vs non-linear models

📁 Regressions

• Linear regression implementations
• Logistic regression
• Neural networks with hidden layers
• House price prediction models

📁 Recurrent_Neural_netwrok

• Text prediction using RNNs
• Sequence modeling examples

📁 machine learning

• Scikit-learn implementations
• Support Vector Machines (SVM)
• Decision Trees (Classification & Regression)
• K-Nearest Neighbors (KNN)
• Naive Bayes Classification
• Various datasets and examples

📁 word_embedding

• Text to vector conversion
• Word embeddings with NumPy
• Word embeddings with PyTorch

📁 Scripts

• Virtual environment activation scripts
• Python executable files
• PyTorch and related tools

Getting Started

1. Clone the repository:

git clone https://github.com/danishshaikh06/Machine-learning-Pytorch-using-deep-learning.git

2. Navigate to the project directory:

cd Machine-learning-Pytorch-using-deep-learning

3. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

4. Install required dependencies:

pip install torch torchvision scikit-learn numpy pandas matplotlib seaborn

Requirements

• Python 3.7+
• PyTorch
• scikit-learn
• NumPy
• Pandas
• Matplotlib
• Seaborn

Usage

Each directory contains standalone Python scripts that can be run independently. Navigate to the specific directory and run the desired script:

python script_name.py

Contributing

Feel free to contribute to this repository by:

• Adding new machine learning models
• Improving existing implementations
• Adding documentation
• Fixing bugs

License

This project is open source and available under the MIT License.