Bakhtiyar

Hello, try to use the same seed for both cases `dde.config.set_random_seed(1)`. Maybe the results are different due to different initialization

Hello, @praksharma For a 3D cylinder, what would be the BC location function for the bottom wall (z = 0) ? `def bottom_wall(X, on_boundary):` ` return np.isclose(X[2], 0) and on_boundary`...

So you convert the wall surface to static particles, introduce fluid particles, then run simulations with splishsplash to gather data. Compress the data and finally supply it as input to...

Thank you

Still a bit confused. In the code, there is the `run_simulator` function that uses a `scene.json` file and an output directory. The json file contains information about fluids in `.bgeo`...

yes, but it is for a trained network, right? I mean in the data generation stage, https://github.com/isl-org/DeepLagrangianFluids/blob/d651c6fdf2aca3fac9abe3693b20981b191b4769/datasets/create_physics_scenes.py#L430 scenes are run with fluid particles interacting with each other and with boundary...

After a scene was created, we have data only of fluid particles? The `.bgeo` geometry file is later converted to particles https://github.com/isl-org/DeepLagrangianFluids/blob/d651c6fdf2aca3fac9abe3693b20981b191b4769/datasets/create_physics_records.py#L19 and added to the `feat_dict` ? https://github.com/isl-org/DeepLagrangianFluids/blob/d651c6fdf2aca3fac9abe3693b20981b191b4769/datasets/create_physics_records.py#L56

`tf.where(condition, pde_set_1, pde_set_2)`?