Metadata-Version: 2.1
Name: neural-dsl
Version: 0.2.7
Summary: A domain-specific language and debugger for neural networks
Home-page: https://github.com/Lemniscate-SHA-256/Neural
Author: Lemniscate-SHA-256/SENOUVO Jacques-Charles Gad
Author-email: Lemniscate_zero@proton.me
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE.md
Requires-Dist: click>=8.1.3
Requires-Dist: flask>=3.0
Requires-Dist: flask-cors>=3.1
Requires-Dist: flask-httpauth>=4.4
Requires-Dist: graphviz>=0.20
Requires-Dist: lark>=1.1.5
Requires-Dist: matplotlib<3.10
Requires-Dist: networkx>=2.8.8
Requires-Dist: numpy>=1.23.0
Requires-Dist: psutil>=5.9.0
Requires-Dist: pytest>=7.0.0
Requires-Dist: pyyaml>=6.0.1
Requires-Dist: python-dotenv>=1.0
Requires-Dist: pysnooper
Requires-Dist: radon>=5.0
Provides-Extra: full
Requires-Dist: dash>=2.18.2; extra == "full"
Requires-Dist: dash-bootstrap-components>=1.0.0; extra == "full"
Requires-Dist: flask-socketio>=5.0.0; extra == "full"
Requires-Dist: plotly>=5.18; extra == "full"
Requires-Dist: torch>=1.10.0; extra == "full"
Requires-Dist: pygithub>=1.59; extra == "full"
Requires-Dist: selenium>=4.0; extra == "full"
Requires-Dist: optuna>=3.0; extra == "full"
Requires-Dist: fastapi>=0.68; extra == "full"
Requires-Dist: webdriver-manager; extra == "full"
Requires-Dist: tensorflow>=2.6; extra == "full"
Requires-Dist: huggingface_hub>=0.16; extra == "full"
Requires-Dist: transformers>=4.30; extra == "full"
Requires-Dist: torchvision>=0.15; extra == "full"
Requires-Dist: multiprocess>=0.70; extra == "full"
Requires-Dist: tweepy==4.15.0; extra == "full"
Requires-Dist: pandas>=1.3; extra == "full"
Requires-Dist: scikit-learn>=1.0; extra == "full"
Requires-Dist: scipy>=1.7; extra == "full"
Requires-Dist: seaborn>=0.11; extra == "full"
Requires-Dist: statsmodels>=0.13; extra == "full"
Requires-Dist: sympy>=1.9; extra == "full"
Requires-Dist: onnx>=1.10; extra == "full"
Requires-Dist: onnxruntime>=1.10; extra == "full"

<div align="center">
  <img src="https://github.com/user-attachments/assets/f92005cc-7b1c-4020-aec6-0e6922c36b1b" alt="Neural Logo" width="200"/>
  <h1>Neural: A Neural Network Programming Language</h1>
  <p><strong>Simplify deep learning development with a powerful DSL, cross-framework support, and built-in debugging</strong></p>

  [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
  [![Python 3.8+](https://img.shields.io/badge/Python-3.8%2B-green.svg)](https://www.python.org/)
  [![Discord](https://img.shields.io/badge/Chat-Discord-7289DA)](https://discord.gg/KFku4KvS)
  [![Pylint](https://github.com/Lemniscate-world/Neural/actions/workflows/pylint.yml/badge.svg?branch=main)](https://github.com/Lemniscate-world/Neural/actions/workflows/pylint.yml)
  [![Python package](https://github.com/Lemniscate-world/Neural/actions/workflows/python-package.yml/badge.svg?branch=main)](https://github.com/Lemniscate-world/Neural/actions/workflows/python-package.yml)
  [![CodeQL Advanced](https://github.com/Lemniscate-world/Neural/actions/workflows/codeql.yml/badge.svg)](https://github.com/Lemniscate-world/Neural/actions/workflows/codeql.yml)
  [![Tests](https://github.com/Lemniscate-world/Neural/actions/workflows/pytest.yml/badge.svg?branch=main)](https://github.com/Lemniscate-world/Neural/actions/workflows/pytest-to-issues.yml)
  [![Coverage](https://img.shields.io/codecov/c/github/Lemniscate-world/Neural)](https://codecov.io/gh/Lemniscate-world/Neural)

  <a href="https://www.producthunt.com/posts/neural-2?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-neural&#0045;2" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=945073&theme=dark&t=1742808173867" alt="Neural - DSL for defining, training, debugging neural networks | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
</div>

> ⚠️ **BETA STATUS**: Neural-dsl is under active development—bugs may exist, feedback welcome! Not yet recommended for production use.

![Neural Demo](https://github.com/user-attachments/assets/ecbcce19-73df-4696-ace2-69e32d02709f)

## 📋 Table of Contents
- [Overview](#overview)
- [Pain Points Solved](#pain-points-solved)
- [Key Features](#features)
- [Installation](#installation)
- [Quick Start](#quick-start)
- [Debugging with NeuralDbg](#-debugging-with-neuraldbg)
- [Why Neural?](#why-neural)
- [Documentation](#documentation)
- [Examples](#examples)
- [Contributing](#contributing)
- [Community](#community)
- [Support](#support)

## Overview
Neural is a domain-specific language (DSL) designed for defining, training, debugging, and deploying neural networks. With declarative syntax, cross-framework support, and built-in execution tracing (NeuralDbg), it simplifies deep learning development whether via code, CLI, or a no-code interface.

##  Pain Points Solved

Neural addresses deep learning challenges across **Criticality** (how essential) and **Impact Scope** (how transformative):

| Criticality / Impact | Low Impact                  | Medium Impact                       | High Impact                         |
|----------------------|-----------------------------|-------------------------------------|-------------------------------------|
| **High**             |                             |                                     | - **Shape Mismatches**: Pre-runtime validation stops runtime errors.<br>- **Debugging Complexity**: Real-time tracing & anomaly detection. |
| **Medium**           |                             | - **Steep Learning Curve**: No-code GUI eases onboarding. | - **Framework Switching**: One-flag backend swaps.<br>- **HPO Inconsistency**: Unified tuning across frameworks. |
| **Low**              | - **Boilerplate**: Clean DSL syntax saves time. | - **Model Insight**: FLOPs & diagrams.<br>- **Config Fragmentation**: Centralized setup. |                                     |

### Why It Matters
- **Core Value**: Fix critical blockers like shape errors and debugging woes with game-changing tools.
- **Strategic Edge**: Streamline framework switches and HPO for big wins.
- **User-Friendly**: Lower barriers and enhance workflows with practical features.

## Feedback

Help us improve Neural DSL! Share your feedback: [Typeform link](https://form.typeform.com/to/xcibBdKD#name=xxxxx&email=xxxxx&phone_number=xxxxx&user_id=xxxxx&product_id=xxxxx&auth_code=xxxxx).



## Features

- **YAML-like Syntax**: Define models intuitively without framework boilerplate.
- **Shape Propagation**: Catch dimension mismatches *before* runtime.
  - ✅ Interactive shape flow diagrams included.
- **Multi-Framework HPO**: Optimize hyperparameters for both PyTorch and TensorFlow with a single DSL config (#434).
![Peek06-04-202517-00-ezgif com-speed](https://github.com/user-attachments/assets/5c4f51b5-e40f-47b3-872d-445f71c6582f)
- **Enhanced Dashboard UI**: Improved NeuralDbg dashboard with a more aesthetic dark theme design (#452).
- **Blog Support**: Infrastructure for blog content with markdown support and Dev.to integration (#445).
- **Multi-Backend Export**: Generate code for **TensorFlow**, **PyTorch**, or **ONNX**.
- **Training Orchestration**: Configure optimizers, schedulers, and metrics in one place.
- **Visual Debugging**: Render interactive 3D architecture diagrams.
- **Extensible**: Add custom layers/losses via Python plugins.
- **NeuralDbg**: Built-in Neural Network Debugger and Visualizer.
- **No-Code Interface**: Quick Prototyping for researchers and an educational, accessible tool for beginners.

---

### **NeuralDbg: Built-in Neural Network Debugger**
NeuralDbg provides **real-time execution tracing, profiling, and debugging**, allowing you to visualize and analyze deep learning models in action. Now with an enhanced dark theme UI for better visualization (#452).

✅ **Real-Time Execution Monitoring** – Track activations, gradients, memory usage, and FLOPs.
![test_trace_graph](https://github.com/user-attachments/assets/15b1edd2-2643-4587-9843-aa4697ed2e4b)
![test_flops_memory_chart](https://github.com/user-attachments/assets/de1f6504-787b-4948-b543-fe3d2f8bfd74)
![test_trace_graph_stacked](https://github.com/user-attachments/assets/529fc487-fb31-48ad-bb11-b0c64ab330ed)
![test_trace_graph_heatmap](https://github.com/user-attachments/assets/debef7d5-9989-45da-ae91-7cef19aac2b0)
![test_anomaly_chart](https://github.com/user-attachments/assets/b57d3142-6da8-4d57-94f0-486d1797e92c)
![test_dead_neurons](https://github.com/user-attachments/assets/f4629b4f-2988-410e-8b49-3dde225f926f)
![test_gradient_chart](https://github.com/user-attachments/assets/ca6b9f20-7dd8-4c72-9ee8-a3f35af6208b)


✅ **Shape Propagation Debugging** – Visualize tensor transformations at each layer.
✅ **Gradient Flow Analysis** – Detect **vanishing & exploding gradients**.
✅ **Dead Neuron Detection** – Identify inactive neurons in deep networks.
✅ **Anomaly Detection** – Spot **NaNs, extreme activations, and weight explosions**.
✅ **Step Debugging Mode** – Pause execution and inspect tensors manually.


## Installation

**Prerequisites**: Python 3.8+, pip

### Option 1: Install from PyPI (Recommended)

```bash
# Install the latest stable version
pip install neural-dsl

# Or specify a version
pip install neural-dsl==0.2.6  # Latest version with enhanced dashboard UI
```

### Option 2: Install from Source

```bash
# Clone the repository
git clone https://github.com/Lemniscate-world/Neural.git
cd Neural

# Create a virtual environment (recommended)
python -m venv venv
source venv/bin/activate  # Linux/macOS
venv\Scripts\activate     # Windows

# Install dependencies
pip install -r requirements.txt
```

## Quick Start

### 1. Define a Model

Create a file named `mnist.neural` with your model definition:

```yaml
network MNISTClassifier {
  input: (28, 28, 1)  # Channels-last format

  layers:
    Conv2D(filters=32, kernel_size=(3,3), activation="relu")
    MaxPooling2D(pool_size=(2,2))
    Flatten()
    Dense(units=128, activation="relu")
    Dropout(rate=0.5)
    Output(units=10, activation="softmax")

  loss: "sparse_categorical_crossentropy"
  optimizer: Adam(learning_rate=0.001)
  metrics: ["accuracy"]

  train {
    epochs: 15
    batch_size: 64
    validation_split: 0.2
  }
}
```

### 2. Run or Compile the Model

```bash
# Generate and run TensorFlow code
neural run mnist.neural --backend tensorflow --output mnist_tf.py

# Or generate and run PyTorch code
neural run mnist.neural --backend pytorch --output mnist_torch.py
```

### 3. Visualize Architecture

```bash
neural visualize mnist.neural --format png
```

This will create visualization files for inspecting the network structure and shape propagation:
- `architecture.png`: Visual representation of your model
- `shape_propagation.html`: Interactive tensor shape flow diagram
- `tensor_flow.html`: Detailed tensor transformations

### 4. Debug with NeuralDbg

```bash
neural debug mnist.neural
```

Open your browser to http://localhost:8050 to monitor execution traces, gradients, and anomalies interactively.

### 5. Use the No-Code Interface

```bash
neural --no_code
```

Open your browser to http://localhost:8051 to build and compile models via a graphical interface.

---

## **🛠 Debugging with NeuralDbg**

### **🔹 1️⃣ Start Real-Time Execution Tracing**
```bash
python neural.py debug mnist.neural
```
**Features:**
✅ Layer-wise execution trace
✅ Memory & FLOP profiling
✅ Live performance monitoring

### **🔹 2️⃣ Analyze Gradient Flow**
```bash
python neural.py debug --gradients mnist.neural
```
 **Detect vanishing/exploding gradients** with interactive charts.

### **🔹 3️⃣ Identify Dead Neurons**
```bash
python neural.py debug --dead-neurons mnist.neural
```
🛠 **Find layers with inactive neurons (common in ReLU networks).**

### **🔹 4️⃣ Detect Training Anomalies**
```bash
python neural.py debug --anomalies mnist.neural
```
 **Flag NaNs, weight explosions, and extreme activations.**

### **🔹 5️⃣ Step Debugging (Interactive Tensor Inspection)**
```bash
python neural.py debug --step mnist.neural
```
🔍 **Pause execution at any layer and inspect tensors manually.**

---

##  Why Neural?

| Feature               | Neural      | Raw TensorFlow/PyTorch |
|-----------------------|-------------|-------------------------|
| Shape Validation      | ✅ Auto     | ❌ Manual               |
| Framework Switching   | 1-line flag | Days of rewriting       |
| Architecture Diagrams | Built-in    | Third-party tools       |
| Training Config       | Unified     | Fragmented configs      |


### **🔄 Cross-Framework Code Generation**
| Neural DSL          | TensorFlow Output          | PyTorch Output            |
|---------------------|----------------------------|---------------------------|
| `Conv2D(filters=32)`| `tf.keras.layers.Conv2D(32)`| `nn.Conv2d(in_channels, 32)` |
| `Dense(units=128)`  | `tf.keras.layers.Dense(128)`| `nn.Linear(in_features, 128)`|

##  Benchmarks
| Task                 | Neural | Baseline (TF/PyTorch) |
|----------------------|--------|-----------------------|
| MNIST Training       | 1.2x ⚡| 1.0x                  |
| Debugging Setup      | 5min 🕒| 2hr+                  |

##  Documentation

- [DSL Documentation](docs/dsl.md)
- [Blog](docs/blog/README.md)

Explore advanced features:
- [Custom Layers Guide]()
- [ONNX Export Tutorial]()
- [Training Configuration]()
- [NeuralDbg Debugging Features]()

##  Examples

Explore common use cases in `examples/` with step-by-step guides in `docs/examples/`:
- [MNIST Classifier Guide](docs/examples/mnist_guide.md)
- [Sentiment Analysis Guide](docs/examples/sentiment_guide.md)
- [Transformer for NLP Guide](docs/examples/transformer_guide.md)

## 🕸 Architecture Graphs

![classes](https://github.com/Lemniscate-world/Neural/blob/main/classes.png)
![packages](https://github.com/Lemniscate-world/Neural/blob/main/packages.png)

*Note: You may need to zoom in to see details in these architecture diagrams.*

## Repository Structure

The Neural repository is organized into the following main directories:

- **`docs/`**: Documentation files
- **`examples/`**: Example Neural DSL files
- **`neural/`**: Main source code
  - **`neural/cli/`**: Command-line interface
  - **`neural/parser/`**: Neural DSL parser
  - **`neural/shape_propagation/`**: Shape propagation and validation
  - **`neural/code_generation/`**: Code generation for different backends
  - **`neural/visualization/`**: Visualization tools
  - **`neural/dashboard/`**: NeuralDbg dashboard
  - **`neural/hpo/`**: Hyperparameter optimization
- **`neuralpaper/`**: NeuralPaper.ai implementation
- **`profiler/`**: Performance profiling tools
- **`tests/`**: Test suite

For a detailed explanation of the repository structure, see [REPOSITORY_STRUCTURE.md](REPOSITORY_STRUCTURE.md).

Each directory contains its own README with detailed documentation:

- [neural/cli](neural/cli/README.md): Command-line interface
- [neural/parser](neural/parser/README.md): Neural DSL parser
- [neural/code_generation](neural/code_generation/README.md): Code generation
- [neural/shape_propagation](neural/shape_propagation/README.md): Shape propagation
- [neural/visualization](neural/visualization/README.md): Visualization tools
- [neural/dashboard](neural/dashboard/README.md): NeuralDbg dashboard
- [neural/hpo](neural/hpo/README.md): Hyperparameter optimization
- [neuralpaper](neuralpaper/README.md): NeuralPaper.ai implementation
- [profiler](profiler/README.md): Performance profiling tools
- [docs](docs/README.md): Documentation
- [examples](examples/README.md): Example models
- [tests](tests/README.md): Test suite



---


##  Contributing

We welcome contributions! See our:
- [Contributing Guidelines](CONTRIBUTING.md)
- [Code of Conduct](CODE_OF_CONDUCT.md)
- [Roadmap](ROADMAP.md)

To set up a development environment:
```bash
git clone https://github.com/Lemniscate-world/Neural.git
cd Neural
pip install -r requirements-dev.txt  # Includes linter, formatter, etc.
pre-commit install  # Auto-format code on commit
```

## Star History

[![Star History Chart](https://api.star-history.com/svg?repos=Lemniscate-world/Neural&type=Timeline)](https://www.star-history.com/#Lemniscate-world/Neural&Timeline)

## Support

If you find Neural useful, please consider supporting the project:

- ⭐ **Star the repository**: Help us reach more developers by starring the project on GitHub
- 🔄 **Share with others**: Spread the word on social media, blogs, or developer communities
- 🐛 **Report issues**: Help us improve by reporting bugs or suggesting features
- 🤝 **Contribute**: Submit pull requests to help us enhance Neural (see [Contributing](#contributing))

### Repository Status

This repository has been cleaned and optimized for better performance. Large files have been removed from the Git history to ensure a smoother experience when cloning or working with the codebase.

## Community

Join our growing community of developers and researchers:

- [Discord Server](https://discord.gg/KFku4KvS): Chat with developers, get help, and share your projects
- [Twitter @NLang4438](https://x.com/NLang4438): Follow for updates, announcements, and community highlights
- [GitHub Discussions](https://github.com/Lemniscate-world/Neural/discussions): Participate in discussions about features, use cases, and best practices

<div align="center">
  <img src="https://github.com/user-attachments/assets/9edd42b3-dd23-4f4a-baad-422e690d687c" alt="Neural Logo" width="150"/>
  <p><em>Building the future of neural network development, one line of DSL at a time.</em></p>
</div>


**Note**: See v0.2.7 release notes for latest fixes and improvements!
