You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi team, hope you are well and had a nice new year. I have been trying to make neural networks to estimate the channel coefficients for various paths by LOS, Reflection, and diffractions. I was successfully able to do this LOS and reflection channel coefficients But when training my models for diffraction, I noticed that the model wasn't giving the expected output. after further research, and according to the documentation, instead of objects, diffraction occurs on wedges. upon looking at the source code, I saw that wedges are defined by the angle and the length (but not sure.) As my model wasnt giving the expected outputs, I tried using the paths formed by wedges of the same ID which is shown in the figure as well (real part)and the expected and predicted values aline quite well, so I suppose its properties of wedges that I am missing to train the models. Can you please guide me on how I can get these properties of a specific ID wedge? It would be really appreciated.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi team, hope you are well and had a nice new year. I have been trying to make neural networks to estimate the channel coefficients for various paths by LOS, Reflection, and diffractions. I was successfully able to do this LOS and reflection channel coefficients But when training my models for diffraction, I noticed that the model wasn't giving the expected output. after further research, and according to the documentation, instead of objects, diffraction occurs on wedges. upon looking at the source code, I saw that wedges are defined by the angle and the length (but not sure.) As my model wasnt giving the expected outputs, I tried using the paths formed by wedges of the same ID which is shown in the figure as well (real part)and the expected and predicted values aline quite well, so I suppose its properties of wedges that I am missing to train the models. Can you please guide me on how I can get these properties of a specific ID wedge? It would be really appreciated.
Beta Was this translation helpful? Give feedback.
All reactions