torchsde

torchsde copied to clipboard

How to do double stochastic integrals?

1

Is it possible to use or modify this code to do double stochastic integrals in a reasonable way, in order to support higher order SDE solvers? I am using your...

crowsonkb

DEPRECATION: torchsde 0.2.5 has a non-standard dependency specifier numpy>=1.19.*; python_version >= "3.7". pip 24.1 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of...

Cuiyim

I got the following errors: File ".venv\lib\site-packages\torchsde\_core\adjoint.py", line 271, in sdeint_adjoint extra_solver_state = solver.init_extra_solver_state(ts[0], y0) File ".venv\lib\site-packages\torchsde\_core\methods\reversible_heun.py", line 59, in init_extra_solver_state return self.sde.f_and_g(t0, y0) + (y0,) File ".venv\lib\site-packages\torchsde\_core\base_sde.py", line 92,...

chunqishi

WARNING: Error parsing dependencies of torchsde

1

WARNING: Error parsing dependencies of torchsde: .* suffix can only be used with `==` or `!=` operators numpy (>=1.19.*) ; python_version >= "3.7" ~~~~~~~^ python3 -V Python 3.10.10

bluusun

extra_solver_state Documentation

1

Is the documentation for `extra_solver_state` going to come out at some point? Alternatively, are there any useful referencez to try and use this functionality? I would be particularly interested in...

francescabasini

learning the generative model of periodical process

1

I've applied the WGAN algorithm implemented in torchsde/example/sde_gap.py to sine function (deterministic with fixed initial conditions). After 30000 learning epochs we can see that algorithm struggles to capture the periodic...

qtomcatq

DEPRECATION: distro-info 0.23ubuntu1 has a non-standard version number. pip 24.1 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of distro-info or contact the...

Rickymuhindo

Compatibility Bugs

1

kornia library has refactored some functions and the example/cont_ddpm.py was not working anymore due to an error raised in example/unet.py that needs to be changed to `return kornia.filters.filter2d(x, self.f, normalized=True)`.

matteoguarrera