Prakhar Sharma

So you are diving into the source code. Yes, the output units are constrained using ICs and BCs. > the `train_x` concludes all the BC and initial points and domain...

Can you please paste your code in correct format? It is incredibly difficult to read the code.

You can use [`PointSetBC`](https://github.com/lululxvi/deepxde/blob/5b21146dd2c73e8df7d31acaad8b5604d30fc3e8/deepxde/icbc/boundary_conditions.py#L164). The inputs are ```sh PointSetBC(points, values) ``` Here you can directly input the coordinates and the BCs.

Good question. I am not entirely sure, but may be you could use the Operator BC. But I have never used [`PointSetOperatorBC`](https://github.com/lululxvi/deepxde/blob/5b21146dd2c73e8df7d31acaad8b5604d30fc3e8/deepxde/icbc/boundary_conditions.py#L236C7-L236C25). If I you were you, I would try...

@Gregouare You are probably using an older version of DeepXDE. The PointCloud class has boundary_normal defined. https://github.com/lululxvi/deepxde/blob/3810a9888d13e04cecf114e93a00dfbf90021472/deepxde/geometry/pointcloud.py#L65 Depending on whether you are using conda or just python virtualenv the upgrade...

If you mean the output from each neuron, you should look for code which does the forward pass. The forward pass is mostly included in the class definition of the...

Sorry this is not my background, but why do you need ambient temperature as the input to the network? Can you write the PDEs your are trying to solve? Also,...

Yes you just need a train the problem for a longer duration. If you provide us with the code, I can look into and give you insights.

Hey, PINNs are meshless. This means you don't need lines, surfaces , planes etc. Just pass your the nodal coordinates as anchors. Here is an example, ```python data = dde.data.PDE(...

The error is pretty obvious. You are using function within function. Try this. ```python bc_l = dde.icbc.DirichletBC(geom, lambda x: 5, boundary_l) bc_r = dde.icbc.NeumannBC(geom, lambda x: 0, boundary_r) ```