Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

mat_rework_inverse_mode #36

Merged
merged 6 commits into from
Oct 16, 2023
Merged

mat_rework_inverse_mode #36

merged 6 commits into from
Oct 16, 2023

Conversation

aminevdam
Copy link
Contributor

  1. Переработал метод mat для решения систем и совместил с адаптивными лямбдами.
  2. PINN mode для решения обратной задачи. На данный момент данные о решении подаются как граничные условия.
  3. Небольшой рефакторинг для ускорения вычислений (избавился от ненужных циклов)
  4. Добавил несколько экспериментов с методом mat для систем.

mat_for_system_and_adaptive_lamdas__inverse_task
tedeous/eval.py Outdated
@@ -4,9 +4,11 @@
from tedeous.points_type import Points_type
from tedeous.derivative import Derivative
from tedeous.device import device_type, check_device
from tedeous.utils import tensor_to_dict
from torchtext.transforms import PadTransform
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

А нам правда не обойтись здесь без PadTransform и надо тащить целую зависимость torchtext?

Copy link
Member

@SuperSashka SuperSashka left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Попутно в обсуждении пофиксили кэш, по нему не будет комментов. Считаю, что (а) мы этим pr закрыли только #28 . Надо разобраться с torchtext и можно вливать. И (б) #31 мы не закрыли. По PINN напишу в #31 что надо сделать, чтобы его закрыть.

Copy link
Member

@SuperSashka SuperSashka left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we finished with 'mat' #28 mode at the time being and start working towards PINN #31 mode, it still subject to change, but now we can make separate 'data' BC with its own lambda, which is good.

This was referenced Oct 13, 2023
@aminevdam aminevdam merged commit adde88e into ITMO-NSS-team:main Oct 16, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants