neural-dimensionality-tracker 0.1.0

High-frequency monitoring of neural network representational dimensionality

Neural Dimensionality Tracker (NDT)

High-frequency monitoring of neural network representational dimensionality during training. Track how your network's internal representations evolve, detect phase transitions, and gain insights into the learning dynamics of deep neural networks.

Features

• Minimal Intrusion: Add dimensionality tracking to any PyTorch model with just 3 lines of code
• Architecture-Agnostic: Automatic support for MLPs, CNNs, Transformers, and Vision Transformers
• Multiple Metrics: Track 4 complementary dimensionality measures
• Jump Detection: Automatically identify phase transitions during training
• Rich Visualization: Built-in plotting with Matplotlib and interactive Plotly dashboards
• Flexible Export: Save results as CSV, JSON, or HDF5
• Production-Ready: Fully typed, tested (>90% coverage), and documented

Installation

pip install neural-dimensionality-tracker

Quick Start

import torch.nn as nn
from ndt import HighFrequencyTracker

# Your model
model = nn.Sequential(
    nn.Linear(784, 512), nn.ReLU(),
    nn.Linear(512, 256), nn.ReLU(),
    nn.Linear(256, 10)
)

# Create tracker
tracker = HighFrequencyTracker(model, sampling_frequency=10)

# Training loop
for step, (x, y) in enumerate(dataloader):
    output = model(x)
    loss = criterion(output, y)
    loss.backward()
    optimizer.step()

    tracker.log(step, loss.item())  # One line!

# Analyze
results = tracker.get_results()
from ndt import plot_phases
plot_phases(results, metric="stable_rank")

Documentation

See examples/ for complete working examples and detailed usage guides.

License

MIT License - see LICENSE file for details