Model from visual wake word does not work for Harvard tinyMLx course arduino code
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 25/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- arduino, c
- Domain
- embedded-iot, machine-learning
Research direction
Start by comparing vww_model.cc and its corresponding settings file with the model files used by the Harvard tinyMLx Arduino course code. Check whether the generated model and settings are intended to be interchangeable; done means determining whether direct replacement is supported and identifying the compatibility issue if it is not.
Written by the indexing model from the issue text.
Description
I am trying to modify the benchmark training code to create a custom model for person detection.
Just to check for sanity, I was trying to see whether I can port the already generated model to arduino code.
I have used the vww_model.cc file and the corresponding settings file to replace the model files in the arduino code developed for the course https://www.edx.org/professional-certificate/harvardx-tiny-machine-learning
I have used the board from here: https://store-usa.arduino.cc/products/arduino-tiny-machine-learning-kit
We have arduino code already available for this course.
This code already has model file. So I replace it with the model file available in this repo and also change the settings files.
The output of the code always shows no person, even when I change the position of the camera.
Can anybody let me know whether this model can be directly used to replace the model files in other repo.
- Dominant language
- C
- Stars
- 479
- Forks
- 116
- PR merge metrics
- No merged PRs in 30d
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from mlcommons/tiny
-
Difficulty 1/5 Under an hour Newbie friendliness 68/100
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
Difficulty 4/5 3-5 days Newbie friendliness 25/100
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
Similar issues
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
bradcypert/plum#53 ·
-
Component: GLib
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
-
Status: Opened
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
nextbsd/nextbsd-userland#285 ·