torchdyn
torchdyn copied to clipboard
A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods
Is it safe to use the ODE solvers with a complex tensor? For example ```python def f(t, x): print(t) return 3 * x x0 = torch.from_numpy(np.array([1 + 1j, 2 +...
* Fixes a small typo in `README.md`
Fixes the following error which I ran into: ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all() The k1 array passed...
In tutorials m2b and m4c the forward pass of the multiple shooting is shown. However, the example doesn't show how to do backpropagation for those examples. Can you show how...
**Describe the bug** In m1a_neural_ode_cookbook : Links to the advanced models are not working **Step to Reproduce** Steps to reproduce the behavior: 1.Go to https://github.com/DiffEqML/torchdyn/blob/master/tutorials/module1-neuralde/m1a_neural_ode_cookbook.ipynb 2. Click on 3. Multiple...
- Fix docstrings for `atol` and `rtol`. - Use `isinstance` instead of `type(x) == t`. - Reorder code to reduce warnings. Additionally, should we remove the warning about fixed step...