-
Notifications
You must be signed in to change notification settings - Fork 3.5k
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
[microTVM] Custom IDE Tutorial #13857
Conversation
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment. Generated by tvm-bot |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
added some initial comments
c09cab0
to
c33dfa4
Compare
c33dfa4
to
a34f404
Compare
a34f404
to
7e3eae4
Compare
from PIL import Image | ||
import tarfile | ||
|
||
import tvm |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do you want to link to or note above that you also need TVM python package installed?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think tvm install would show up by default in google collab version?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
also, I guess that needs to be TVM built with USE_MICRO enabled
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@mehrdadh right, but what if someone wants to run locally?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I added a link to tvm documentation page for installing tvm.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks @mkatanbaf and @alanmacd!
# | ||
# * Open the project Properties. (by right clicking on the project name and selecting "Properties" or by selecting Project -> Properties from the menu bar). | ||
# * Select C/C++ General -> Paths and Symbols. Select the Source Location tab. | ||
# * If you extract the model inside the project folder on your disk, click "Add Folder" and select the "model" folder. (You might need to right click on the project name and select "Refresh" before it appears.) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I couldn't get the "Add Folder" method to work on MacOS, even after restarting the IDE.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not sure why it didn't work for you. Please make sure the extracted "model" folder is inside your project folder, and refresh the project explorer.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yea doing the "Refresh" made it show up this time.
Great tutorial @mkatanbaf, I left a few comments and was able to get it up and running on MacOS:
|
Thanks @alanmacd for the detailed review |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, great tutorial!
Adds "Bring microTVM to your own development environment" to microTVM tutorials. This tutorial describes the steps required to integrate a model compiled with microTVM into a custom development environment. We use STM32Cube IDE, the VWW model and the nucleo_l4r5zi board.