Gianni De Fabritiis
Gianni De Fabritiis
For me it is fine to remove the lower cutoff for ET On Wed, Dec 1, 2021 at 6:06 PM Philipp Thölke ***@***.***> wrote: > We do not want to...
We tried with the training samples at low distance but did not work, because the NN is many-body. You can fix the two-body but then you have problems with 3...
100 particles is a good case. However, we have two ways of running multiple simulations. In one we batch them where the same molecule is run in a single NN...
On Tue, Feb 22, 2022 at 6:15 PM Peter Eastman ***@***.***> wrote: > That would definitely need code changes to be efficient. You want it to > know it only...
@raimis can yuo make an issue there as you probbably know the details of what you need in NNPOps.
nice and could we batch that? On Wed, Feb 23, 2022 at 4:24 PM Raimondas Galvelis ***@***.***> wrote: > Just before going into NNPOps, I checked how much CUDA Graphs...
neg_dy is the best compromise in my view On Wed, Aug 31, 2022, 20:52 Philipp Thölke ***@***.***> wrote: > Changing the model to return the positive gradient now would silently...
Who runs the model knows what units want to use and set it for the priors On Fri, Oct 7, 2022, 16:28 Peter Eastman ***@***.***> wrote: > ***@***.**** commented on...
can you use that single model as a wrapper for all the models that you would like to use? It's just the entry point. On Mon, Oct 3, 2022 at...
The code is unit-neutral, whatever you use as input it spits out as output On Mon, Oct 3, 2022 at 6:48 PM Peter Eastman ***@***.***> wrote: > And another question:...