Luca Thiede

Hey, when I train ORGAN via `python scripts/run.py --model organ --train_path ./my_organ/data/hce_smiles.smi --checkpoint_dir ./my_orgapt --device cuda:0 --metrics ./my_organ/metrics` it throws the error ``` Traceback (most recent call last): File "scripts/run.py",...

Results far off

1

After training with the defeault settings but increased epochs the results all look like this:  Did anybody get more accurate results?

I am trying to fit a simple toy example in 1d, from different papers I have seen that it should be working, but the model doesn't learn the modes at...

### Description I was running the following code: ``` import jax import jax.numpy as jnp import jax.experimental.jet as jet import haiku as hk rng_key = jax.random.PRNGKey(0) def fn(x): model =...

ODE solver getting stuck for simple term

3

Hey, I am trying to implement a continuous normalizing flow, where the vector field is parameterized as the gradient of a potential function. Depending on the Adjoint method, either I...

Results not as reported

2

I was running the network with all defeault settings on the GC dataset till convergence (up to about 1000 epochs) several times with different random seeds and never got the...

In your paper you show the predicted trajectories together with the ground truth and the past trajectories. Can you upload the scripts you were using for this?

Lennard-Jones example takes a very long time and error estimates seem off

2

**Describe the bug** I tried to run the Lennard-Jones example from the documentation. With all the default settings exactly copied, the algorithm doesn't finish even after an hour of running...

Very slow/wrong convergence for Lennard-Jones potential

1

* UltraNest version: 4.3.2 * Python version: 3.10.14 * Operating System: Ubuntu I am trying to calculate the partition function of two particles interacting in the Lennard-Jones potential. I implemented...