Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

"resetIn" flag on tmRegion doesn't seem to actually work. #999

Open
HolotypeRobotics opened this issue May 30, 2023 · 0 comments
Open

"resetIn" flag on tmRegion doesn't seem to actually work. #999

HolotypeRobotics opened this issue May 30, 2023 · 0 comments

Comments

@HolotypeRobotics
Copy link

HolotypeRobotics commented May 30, 2023

I have been looking for a proper way to reset temporal memory for learning a short sequence. The Region docs it is says that "resetIn" is is supposed to be set with an SDR. Am I supposed to be using setInputArray()? I Tried that, but got parameter resetIn does not exist in Spec for this region
Please explain how I am supposed to set this? I think that I need to set this to be able to learn a short sequence.
Here is my code:

resetInput = SDR(region.getParameterUInt32("numberOfCols"))
resetInput.dense = [1] * region.getParameterUInt32("numberOfCols")
resetInput = engine.Array(resetInput, True)
# Reset the TM
region.setParameterArray("resetIn", resetInput)
@HolotypeRobotics HolotypeRobotics changed the title Please someone explain how to use "resetIn" flag in python. Please someone explain how to use "resetIn" flag in python tmRegion. May 30, 2023
@HolotypeRobotics HolotypeRobotics changed the title Please someone explain how to use "resetIn" flag in python tmRegion. "resetIn" flag doesn't seem to aactually work. Jun 3, 2023
@HolotypeRobotics HolotypeRobotics changed the title "resetIn" flag doesn't seem to aactually work. "resetIn" flag on tmRegion doesn't seem to actually work. Jun 3, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant