<!-- GH_ONLY_START --> <p align="center"> <img width="350" src=https://github.com/DeepTrackAI/DeepTrack2/blob/develop/assets/DeepTrack2-logo.png?raw=true> </p> <!-- GH_ONLY_END --> <h3 align="center">DeepTrack2 - A comprehensive deep learning framework for digital microscopy.</h3> <p align="center"> <a href="/LICENSE" alt="licence"> <img src="https://img.shields.io/github/license/DeepTrackAI/DeepTrack2"> </a> <a href="https://badge.fury.io/py/deeptrack"> <img src="https://badge.fury.io/py/deeptrack.svg" alt="PyPI version"> </a> <a href="https://deeptrackai.github.io/DeepTrack2"> <img src="https://img.shields.io/badge/docs-available-blue?logo=readthedocs"> </a> <a href="https://badge.fury.io/py/deeptrack"> <img src="https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue" alt="Python version"> </a> <a href="https://doi.org/10.1063/5.0034891"> <img src="https://img.shields.io/badge/cite us-10.1063%2F5.0034891-blue"> </a> </p> <p align="center"> <a href="#installation">Installation</a> • <a href="#getting-started">Getting Started</a> • <a href="#examples">Examples</a> • <a href="#advanced-tutorials">Advanced Tutorials</a> • <a href="#developer-tutorials">Developer Tutorials</a> • <a href="#cite-us">Cite us</a> • <a href="/LICENSE">License</a> </p>

DeepTrack2 is a modular Python library for generating, manipulating, and analyzing image data pipelines for machine learning and experimental imaging.

<b>TensorFlow Compatibility Notice:</b> DeepTrack2 version 2.0 and subsequent do not support TensorFlow. If you need TensorFlow support, please install the legacy version 1.7.

The following quick start guide is intended for complete beginners to understand how to use DeepTrack2, from installation to training your first model. Let's get started!

Installation

DeepTrack2 2.0 requires at least python 3.9.

To install DeepTrack2, open a terminal or command prompt and run:

pip install deeptrack

or

python -m pip install deeptrack

This will automatically install the required dependencies.

Getting Started

Here you find a series of notebooks that give you an overview of the core features of DeepTrack2 and how to use them:

• DTGS101 Introduction to DeepTrack2 <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS101_intro.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Overview of how to use DeepTrack 2. Creating images combining DeepTrack2 features, extracting properties, and using them to train a neural network.

• DTGS106 Simulating Different Image Modalities <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS106_particle_image_modalities.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Simulating a spherical particle with different image modalities and generating a movie where this particle diffuses with passive Brownian motion.

• DTGS111 Loading Image Files Using Sources <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS111_datafiles.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Using sources to load image files and to train a neural network.

• DTGS121 Tracking a Point Particle with a CNN <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS121_tracking_particle_cnn.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Tracking a point particle with a convolutional neural network (CNN) using simulated particles resolved through a microscope with aberrations.

• DTGS126 Characterizing Aberrations with a CNN <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS126_characterizing_aberrations_cnn.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Characterizing spherical aberrations of an optical device with a convolutional neural network (CNN) using simulated images in the training process.

• DTGS127 Characterizing Aberrations with Optuna <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS127_characterizing_aberrations_optuna.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Characterizing aberrations of an optical device with the optimization framework Optuna.

• DTGS131 Tracking Multiple Particles with a U-Net <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS131_tracking_multiple_particles_unet.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Tracking multiple particles using a U-net trained on simulated images.

• DTGS141 Distinguishing Particles with a U-Net <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS141_distinguishing_particles_in_brightfield.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Tracking and distinguishing particles of different sizes in brightfield microscopy using a U-net trained on simulated images.

• DTGS151 Unsupervised Object Detection <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS151_unsupervised_object_detection_with_lodestar.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Single-shot unsupervised object detection using LodeSTAR.

• DTGS161 Fitting Using PyTorch Gradients <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS161_torch_fitting.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Using PyTorch gradients to fit a Gaussian generated by a DeepTrack2 pipeline.

• DTGS171A Creating Custom Scatterers <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS171A_custom_scatterers.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Creating custom scatterers of arbitrary shapes.

• DTGS171B Creating Custom Scatterers: Bacteria <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/1-getting-started/DTGS171B_custom_scatterers_bacteria.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Creating custom scatterers in the shape of bacteria.

Examples

These are examples of how DeepTrack2 can be used on real datasets:

• DTEx211 MNIST <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/2-examples/DTEx211_MNIST.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Training a fully connected neural network to identify handwritten digits using MNIST dataset.

• DTEx212 Single Particle Tracking <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/2-examples/DTEx212_single_particle_tracking.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg"></a>

  Tracks experimental videos of a single particle.

  <!-- GH_ONLY_START --> <p align="left"> <img width="300" src=/assets/SPT-ideal.gif?raw=true> <img width="300" src=/assets/SPT-noisy.gif?raw=true> <br/> <a href="https://colab.research.google.com/github/DeepTrackAI/DeepTrack2/blob/develop/tutorials/2-examples/DTEx212_single_particle_tracking.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg"> </a> <a href="https://doi.org/10.1364/OPTICA.6.000506" alt="DeepTrack article"> <img src="https://img.shields.io/badge/article-10.1364/OPTICA.6.000506-blue"> </a> <a href="https://doi.org/10.1063/5.0034891" alt="LodeSTAR article"> <img src="https://img.shields.io/badge/article-10.1063/5.0034891-blue"> </a>