Tim Salzmann

Just realised that "BioMotionLab_NTroje" is the alias for the BMLrub dataset. So please ignore the first question.

Hi Ioannis, Thanks for reaching out. Torch does struggle sometimes with tracing specific model structures. Often there is a way around it by slightly adapating the model structure. Please post...

Hi Ioannis, I got it working in the sense that no error is throw. However, I do not have the time to test ist functionally (e.g. if the correct operations...

This is odd! The code I sent you works for me. Including Jacobians and Hessian. Could you try and upgrade to torch==2.3.0 if you have not already?

I just updated the 'main' branch to reflect these changes. The L4CasADi class has an extra parameter `_error_on_data_dependent_ops`now which you would have to set to `False`.

Hi, I found the underlaying problem for the data dependend error. Please pass `validate_args=False` to any distribution you use as in ``` torch.distributions.MultivariateNormal( loc=prior_mean, covariance_matrix=torch.diag_embed(prior_var), validate_args=False ) ``` This will...

Hi Ioannis, It looks to me like this is a problem with functorch itself [1]. I changed the vmap randomess to `same`. While this will enable your code to run...

Hi, > I am not sure if having the same randomness for every element of the batch gives the desired functionality for the CVAE. Could you elaborate on why you...

Hi, please post a minimal non working code example. Thanks Tim

> The structure is basically identical to another code i'm using for the neural MPC but with the only difference being the type of l4casadi funcion to convert the pytorch...