-
Notifications
You must be signed in to change notification settings - Fork 0
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
E2E Tests: ImageManip node and better checks. #140
Conversation
Codecov ReportAll modified and coverable lines are covered by tests ✅
✅ All tests successful. No failed tests found. Additional details and impacted files@@ Coverage Diff @@
## main #140 +/- ##
==========================================
- Coverage 33.40% 33.04% -0.36%
==========================================
Files 68 69 +1
Lines 3739 3746 +7
==========================================
- Hits 1249 1238 -11
- Misses 2490 2508 +18 ☔ View full report in Codecov by Sentry. |
@klemen1999 I am re-requesting your review since I updated the PR with the addition of |
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, just left one suggestion
dai.ImgFrame.Type.BGR888i | ||
if device.getPlatform().name == "RVC4" | ||
else dai.ImgFrame.Type.BGR888p | ||
) |
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.
Can we set the type based on ˙dai_type˙ field in the NNArchive if present otherwise use this as default?
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.
Will be addressed in the future because dai has not yet implemented it.
Checks added in E2E tests:
Every catch has a
print(e)
so we know whats wrong when running it withmanual.py
This PR also adds
ImageManipV2
node to the pipeline if the model input size is not divisible by 2 (e.g. 513x513 in deeplab) or the input size is too small. We request 2 or 4 times bigger input size from the camera and then resize it down to model's input size withImageManipV2
node.This feature now runs more models in E2E testing.