how exactly does the train_x work?

[AJAXJR24]

Dear @lululxvi Thanks for your help and response. I want to know how train_x works for a problem. In a system of PDE equations with two outputs component is used to define the boundary and initial conditions separately. the train_x concludes all the BC and initial points and domain points and the shape of the each output will be train_x. So how does component work and why the initial and BCs of each component exist in the batch_size for both outputs ? More accurately asking, How does the bc_points work at the beginning of the train_x?

[praksharma]

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 points and the shape of the each output will be train_x

Can you paste the link to the relevant code?

So how does component work and why the initial and BCs of each component exist in the batch_size for both outputs

Again, a link to the particular code might be helpful.

How does the bc_points work at the beginning of the train_x?

What do you mean by beginning of train_x? train_x is a variable containing the training dataset.

[AJAXJR24]

I read the explanations of train_x and it said that the train_x is ordered by bc_points containing BC and initial points and domain points. For example when there is a system of PDE with two outputs y[:,0:1], y[:,1:2]. If the training data has 2000 BC and initial points AND 3000 domain points, the train_x would have 5000 training points. My question is that why both outputs have the same shape since their initial and boundary conditions are different? Better explanation: consider there are two boundary conditions and two initial conditions for each PDE in the system. For each initial conditions 100 points were used total of 200. Why does the shape of the each output contains the 200 points. If from our 2000 bc_points the last 200 is the initial points, what will be the y[-200:,0,1] and y[-200:,1:2]? Ps: I use anchors thus I know my training points and I examined the explanation but struggling to understand the value of outputs on initial points.

[lululxvi]

My question is that why both outputs have the same shape since their initial and boundary conditions are different? Better explanation: consider there are two boundary conditions and two initial conditions for each PDE in the system. For each initial conditions 100 points were used total of 200. Why does the shape of the each output contains the 200 points. If from our 2000 bc_points the last 200 is the initial points, what will be the y[-200:,0,1] and y[-200:,1:2]?

I don't really understand you question and what you are confused about. An easy solution is that you can use a simple 1D example as a test case, and print train_x.