type
status
date
slug
summary
tags
category
icon
password
💡
A simple deep learning framework designed for educational purposes and small-scale experiments. TensorPlay provides basic building blocks for constructing and training neural networks, including tensor operations, layers, optimizers, and training utilities.

⭐ Support This Project

If you find TensorPlay useful for learning and experimentation, please consider supporting the repository by giving it a star on GitHub. Your support motivates continued development and improvements to this educational tool. I'm also open to feedback and suggestions for making TensorPlay even more beginner-friendly and effective for learning deep learning concepts.

🔍 Why TensorPlay is Beginner-Friendly

TensorPlay is a lightweight, educational deep learning framework built from scratch in Python. For newcomers, TensorPlay strips away the complex optimizations and redundant features of industrial - grade frameworks like TensorFlow and PyTorch. It hones in on the core logic of computational graphs, making it a perfect tool to grasp the computational processes of deep learning at a fundamental level.

🚀 Features

  • Core Tensor Structure: Implements a Tensor class with automatic gradient computation, supporting basic arithmetic operations and common activation functions (ReLU, Sigmoid, Tanh, Softmax, GELU).
  • Neural Network Components: Includes essential layers like Dense (fully connected layer) and a Module base class for building custom models.
  • Training Utilities: Provides DataLoader for batching data, training / validation loop helpers (train_on_batch, valid_on_batch), and optimization with Adam optimizer.
  • Early Stopping: Built-in EarlyStopping callback to prevent overfitting.
  • Loss Functions: Implements common loss functions such as MSE (Mean Squared Error), SSE (Sum of Squared Errors), and NLL (Negative Log Likelihood).

🔰 Basic Usage

1. Define a Model

Create custom models by inheriting from Module and defining the forward pass:

2. Prepare Data

Use DataLoader to handle batching and shuffling:

3. Train the Model

Train the model using the train_on_batch function. A typical training loop includes batch training, validation, and early stopping judgment:

4. Evaluate the Model

🧩 Example: KRK Chess Endgame Classification

The demo/KRK_classify.py script demonstrates classifying chess endgame positions (King-Rook-King) as either a draw or not. Key steps:
  1. Data Loading: Parses krkopt.data into numerical features.
  1. Data Preparation: Splits data into training, validation, and test sets.
  1. Model Definition: Uses a 3-layer fully connected network (KRKClassifier).
  1. Training: Uses Adam optimizer with early stopping.
  1. Evaluation: Computes test accuracy.
Run the example:

🔧 Limitations and Future Improvements

Current Limitations

  • Only supports 1D tensors, no higher-dimensional data (matrices, images).
  • Limited layer types (only Dense is implemented).
  • Basic optimizer support (only Adam is available).
  • No GPU acceleration; all operations are CPUbound.
  • Limited debugging tools for computation graphs.

Planned Improvements

  • Add support for n-dimensional tensors (matrices, 3D tensors).
  • Implement more layers (Dropout, BatchNorm).
  • Support GPU acceleration via CUDA for faster training.
  • Improve automatic differentiation efficiency.
  • Include more loss functions (Cross-Entropy, MAE).
  • Add visualization tools for computation graphs and training metrics.

📚 Related Resources

Here are some helpful resources to deepen your understanding of deep learning concepts:

🤝 Contributing

Contributions are welcome! Feel free to open issues for bugs or feature requests, or submit pull requests with improvements.

📝 License

MIT

📥 Download Resources and Source Code

TensorPlay.py
71.5 KB
KRK_calssify.py
4.2 KB

⭐ Support the Repository

GitHub - bluemoon-o2/TensorPlay: A simple deep learning framework designed for educational purposes and small-scale experiments.
A simple deep learning framework designed for educational purposes and small-scale experiments. - bluemoon-o2/TensorPlay
GitHub - bluemoon-o2/TensorPlay: A simple deep learning framework designed for educational purposes and small-scale experiments.
https://github.com/bluemoon-o2/TensorPlay
GitHub - bluemoon-o2/TensorPlay: A simple deep learning framework designed for educational purposes and small-scale experiments.