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

Edge Impulse ML Data Collection #2

Open
plumshum opened this issue Dec 3, 2022 · 8 comments
Open

Edge Impulse ML Data Collection #2

plumshum opened this issue Dec 3, 2022 · 8 comments
Assignees

Comments

@plumshum
Copy link
Contributor

plumshum commented Dec 3, 2022

  1. Go to Edge Impulse website
  2. Sign Up
  3. Immediately prompt you to your first project.
  4. Acquire Data --> Connect to Mobile Phone (will use Raspberry Pi later)
  5. Scan QR Code on Mobile Phone. Change length to 5s. Test it out. Don't test failing yet.
  6. Go to Data Acquisition to see your data
  7. Train until Green then take screenshot.
@chenemii
Copy link
Contributor

chenemii commented Dec 3, 2022

  1. test events (sit, walk, run, jump, fall) - make consistent as possible
  2. form model (must be over 70%)
  3. use model to predict future events

@plumshum
Copy link
Contributor Author

plumshum commented Dec 3, 2022

  1. test events (sit, walk, run, jump, fall) - make consistent as possible
  2. form model
  3. use model to predict future events

Make sure you label each of these movements as separate movements

@chenemii
Copy link
Contributor

chenemii commented Dec 4, 2022

image

@Ktang25
Copy link
Contributor

Ktang25 commented Dec 8, 2022

Screen Shot 2022-12-07 at 10 06 25 PM

@Ktang25
Copy link
Contributor

Ktang25 commented Dec 8, 2022

how would you get data from jumping??

@allytotheson
Copy link
Contributor

image

@celinebuer
Copy link

datawalking

@plumshum
Copy link
Contributor Author

image
gonna change the label later

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

5 participants