Simple-LSTM-AI-Model-Pytorch

A simple LSTM-based sentiment classifier built with PyTorch for learning deep learning fundamentals.

What it does

Classifies text as positive or negative sentiment using:

• Embedding layer for word representations
• LSTM for sequence processing
• Fully connected layer with sigmoid activation for binary classification

Requirements

• Python 3.8+
• PyTorch (CUDA optional for GPU acceleration)

Setup

python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt

Usage

python main.py

This trains the model on a small toy dataset and prints the loss every 10 epochs.

Project Structure

main.py           # Model definition and training loop
requirements.txt  # Python dependencies

License

MIT