-
Notifications
You must be signed in to change notification settings - Fork 1
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
OCR recognition model #158
Conversation
…feat/ocr-recognition
Possible improvements include: |
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.
Generally LGTM, left some comments. One thing that we want to also make sure is the integration with HubAI and depthai-nodes - the archived model should have correct archive data so that the parser can parse it.
Codecov ReportAttention: Patch coverage is
✅ All tests successful. No failed tests found. Additional details and impacted files@@ Coverage Diff @@
## main #158 +/- ##
==========================================
- Coverage 96.31% 94.23% -2.09%
==========================================
Files 147 202 +55
Lines 6304 9349 +3045
==========================================
+ Hits 6072 8810 +2738
- Misses 232 539 +307 ☔ View full report in Codecov by Sentry. |
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.
In general LGTM, left some small comments
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.
Generally LGTM, just couple of small comments
luxonis_train/config/predefined_models/ocr_recognition_model.py
Outdated
Show resolved
Hide resolved
…feat/ocr-recognition
New OCR recognition model, loss, metric and visualizer
The most important changes are summarized below:
Losses:
CTCLoss
with optional focal loss weighting inluxonis_train/attached_modules/losses/ctc_loss.py
and updated__init__.py
to includeCTCLoss
. [1] [2] [3]luxonis_train/attached_modules/losses/README.md
to documentCTCLoss
.Metrics:
OCRAccuracy
metric for OCR tasks inluxonis_train/attached_modules/metrics/ocr_accuracy.py
and updated__init__.py
to includeOCRAccuracy
. [1] [2] [3]luxonis_train/attached_modules/metrics/README.md
to documentOCRAccuracy
.Visualizers:
OCRVisualizer
for visualizing OCR tasks inluxonis_train/attached_modules/visualizers/ocr_visualizer.py
and updated__init__.py
to includeOCRVisualizer
. [1] [2] [3]luxonis_train/attached_modules/visualizers/README.md
to documentOCRVisualizer
.Predefined Models:
OCRRecognitionModel
toluxonis_train/config/predefined_models/__init__.py
and updatedREADME.md
to document its components and parameters. [1] [2] [3]Toy dataset creation example
Examples from the overfitted model on the toy dataset