torchdyn - 1.0.6

Adds torch 2.0 compatibility

- Jupyter Notebook
Published by atong01 almost 3 years ago

torchdyn - 1.0.5

Deprecate python 3.7

- Jupyter Notebook
Published by atong01 almost 3 years ago

torchdyn - 1.4.0.1

- Jupyter Notebook
Published by Zymrael over 3 years ago

torchdyn - Miscellaneous bug fixes

- Jupyter Notebook
Published by Zymrael over 3 years ago

torchdyn - Bug fix - load and save of ODEProblem with adjoint sensitivity

Incorporating #149 and #150 fixing bug preventing save/load of ODEProblem objects ( raised in issue #122).

- Jupyter Notebook
Published by massastrello almost 4 years ago

torchdyn - Bug fixes, odeint API & features, support for python 3.7

• Added the ability to explicitly pass parameters in the form of a dictionary at each ODE solver step
• fixed_odeint can now accept dictionaries as state
• added save_at argument to odeint to have the solver save the solution only at specified time instants
• Data control variable u in NeuralODE has been changed to _control
• Added support for Python 3.7
• various bug fixes

- Jupyter Notebook
Published by massastrello almost 4 years ago

torchdyn - Various fixes, better dependency installs

- Jupyter Notebook
Published by Zymrael almost 5 years ago

torchdyn - 1.0 version: parallel-in-time methods, ODE suite, new tutorials

torchdyn 1.0 is finally out!

- Jupyter Notebook
Published by Zymrael almost 5 years ago

torchdyn - 0.5.1

Minor fixes. More prep for 1.0. Updates PyPI installable version of torchdyn.

- Jupyter Notebook
Published by Zymrael almost 5 years ago

torchdyn - More of everything

More tutorials. MultipleShootingProblem is in. Several fixes to the numerics.

Edit with latest fixes.

- Jupyter Notebook
Published by Zymrael almost 5 years ago

torchdyn - API redesign, more models, numerical methods!

The current release greatly extends the functionality offered by torchdyn, planning for a larger 1.0 release later this month (with multiple shooting layers, root finding, rudimentary implicit solvers, hybrid neural DE solvers).

• New ODEProblem for standard IVPs. Alternative sensitivity algorithms rely ODEProblems for sanity, and are specified at __init__. Backpropagating through the functional API (direct calls to odeint) only uses reverse-mode autodiff.
• A new interpolated adjoint variant relying on torchcde utilities.
• New functional odeint API with adaptive-step solvers: dopri5, tsit5.
• New odeint_hybrid for multi-mode hybrid ODEs with stochastic or deterministic events.
• Seamless hypersolver integration with odeint API, with same call signature!

Some more minor or less interesting changes: * Streamlining of tests and new tutorial automated notebook validation. * s changed to t for more clarity and compatibility with the current literature.

Expect bugs and rough edges (and some WIP hidden in the library). The 1.0 will clean those up.

- Jupyter Notebook
Published by Zymrael almost 5 years ago

torchdyn - torchdyn goes stochastic

- Jupyter Notebook
Published by Zymrael over 5 years ago

torchdyn - torchdyn prepares for SDEs

- Jupyter Notebook
Published by Zymrael almost 6 years ago

torchdyn - torchdyn goes generative

- Jupyter Notebook
Published by Zymrael almost 6 years ago