Releases: DeepTrackAI/DeepTrack2
DeepTrack2 1.5.0
Stable release of DeepTrack2 1.5.0
Release date: 1 November 2022
PyPi 1.5.0
https://pypi.org/project/deeptrack/1.5.0/
DeepTrack2 1.5.0 is a minor release that includes, amongst many other not-so-exciting bug fixes:
- a new time-distributed convolutional neural network model (TimeDistributedFullyConvolutional)
- multi-input support for continuous generators
- several improvements to the Mie physics simulation code
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning."
Applied Physics Reviews 8, 011310 (2021)
https://doi.org/10.1063/5.0034891
DeepTrack2 1.4.1
Stable release of DeepTrack2 1.4.1
Release date: 6 October 2022
PyPi 1.4.1
https://pypi.org/project/deeptrack/1.4.1/
DeepTrack2 1.4.1 is a patch.
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning."
Applied Physics Reviews 8, 011310 (2021)
https://doi.org/10.1063/5.0034891
DeepTrack2 1.4.0
Stable release of DeepTrack2 1.4.0
Release date: 4 October 2022
PyPi 1.4.0
https://pypi.org/project/deeptrack/1.4.0/
DeepTrack2 1.4.0 is a minor release focusing on adding new adding new functionalities and addressing some major bugs.
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning."
Applied Physics Reviews 8, 011310 (2021)
https://doi.org/10.1063/5.0034891
DeepTrack2 1.0.0
Stable release of DeepTrack2 1.0.0
Release date: 1 March 2022
PyPi 1.0.0
https://pypi.org/project/deeptrack/1.0.0/
DeepTrack2 1 is a major release focusing on enhancing performance, stability, and the convenience of using DeepTrack.2
The main new functionalities include:
- Support for GPU-accelerated simulations.
- State-of-the-art methods for tracking and tracing objects.
- Flexile and consistent support for physical units.
- Many new feature classes for arithmetic and statistics.
- New neural network models, including graph neural networks and various generative networks.
- Significantly expanded interactions between features.
If you are already using DeepTrack2 (pypi version 0.x.x), updating to DeepTrack2 1.0.0 (pypi version 1.0.0) should be painless, as no change to your code is needed, if you have followed deprecation warnings.
There are two breaking changes:
- The deprecated operator + to chain features has been removed. It is now only possible using the >> operator.
- The deprecated operator ** to duplicate a feature has been removed. It is now only possible using the ^ operator.
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning."
Applied Physics Reviews 8, 011310 (2021)
https://doi.org/10.1063/5.0034891
DeepTrack2 0.11.5
Stable release of DeepTrack2 0.11.5
Release date: 29 January 2022
PyPi 0.11.5
https://pypi.org/project/deeptrack/0.11.5/
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning."
Applied Physics Reviews 8, 011310 (2021)
https://doi.org/10.1063/5.0034891
DeepTrack2 0.11.3
Stable release of DeepTrack2 0.11.3
Release date: 23 June 2021
PyPi 0.11.3
https://pypi.org/project/deeptrack/0.11.3/
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning."
Applied Physics Reviews 8, 011310 (2021)
https://doi.org/10.1063/5.0034891
DeepTarck2 0.11.0
Stable release of DeepTrack2 0.11.0
Release date: 22 June 2021
PyPi 0.11.0
https://pypi.org/project/deeptrack/0.11.0/
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning."
Applied Physics Reviews 8, 011310 (2021)
https://doi.org/10.1063/5.0034891
DeepTrack2 0.7.4
First stable release of DeepTrack2 (PyPi 0.7.4)
Release date: 19 October 2020
Cite as:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe.
"Quantitative Digital Microscopy with Deep Learning." arXiv:2010.08260
Test version DeepTrack2 0.a191220
This release includes all the core code of DeepTrack 2.0.