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

Is it possible to train offline and then import the NN? #2

Open
rw86347 opened this issue Jan 22, 2018 · 1 comment
Open

Is it possible to train offline and then import the NN? #2

rw86347 opened this issue Jan 22, 2018 · 1 comment

Comments

@rw86347
Copy link

rw86347 commented Jan 22, 2018

Is there someway to do the training offline and then export the NN as a char array?

@t3db0t
Copy link
Owner

t3db0t commented Jan 24, 2018

Do you mean import the trained data into the NN on an Arduino (or wherever)?

In principal, sure; instead of using randomizeWeights to initialize the edge weights, you'd just write the values you want to _net.Layer[l]->Weight[i][j]. If you get it working, feel free to make a pull request, it'd be a cool feature :)

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

2 participants