Vector Observation size of the model does not match

Hello, I’ve been stuck for hours and I can’t find an answer on the internet.

I have this message that appears in the inspector “Vector Observation Size of the model does not match. Was expecting 214 but received 578x1 vector obsertion …”

and when I compile I have an error of “IndexOutOfRangeException: Index was outside the bounds of the array.” on the script Tensor.cs

In the screenshots the loop is repeated 72 times, so 72 * 8 + 2 = 578.
I don’t know if it’s a bug but I really don’t understand
6942518--816143--upload_2021-3-17_0-21-9.png

6942518--816140--upload_2021-3-17_0-20-52.png

It looks like your model was trained with a different observation size, therefore you cannot use it anymore with your current setup. You will need to re-train your agent to get a model that fits the new observation size.