superrob1500
/
mirror-immich
mirror of https://github.com/immich-app/immich
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix(ml): pass model_root_dir to OcrOptions for RapidOCR compatibility (#28610) 

* fix(ml): pass model_root_dir to OcrOptions for RapidOCR compatibility

Fix a TypeError (Path(None)) when the OCR model is invoked, caused by an upstream change in RapidOCR v3.8.1 (RapidAI/RapidOCR@8ea9626).
RapidOCR now internally calls `Path(cfg.get("model_root_dir"))`. Since `model_root_dir` was missing from `OcrOptions`, it evaluated to `None` and triggered a `TypeError: argument should be a str or an os.PathLike`.
This fix adds the missing `model_root_dir` argument to prevent the error.
Ref: #28331

* fix(ml-test): update OCR tests for RapidOCR schema change

* chore(ml-test): remove unused `cache_dir` parameter from `TextRecognizer`

* Revert "chore(ml-test): remove unused `cache_dir` parameter from `TextRecognizer`"

This reverts commit 007ad7b3f2.

* fix(ml): use self.cache_dir for model_root_dir in OcrOptions
pull/28685/head
pneuly 2026-05-29 11:54:04 +09:00 committed by GitHub
parent b189fc571c
commit a838167f11
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
machine-learning/immich_ml/models/ocr/recognition.py
View File

@ -64,6 +64,7 @@ class TextRecognizer(InferenceModel):
rec_batch_num=max_batch_size if max_batch_size else 6, rec_batch_num=max_batch_size if max_batch_size else 6,
rec_img_shape=(3, 48, 320), rec_img_shape=(3, 48, 320),
lang_type=self.language, lang_type=self.language,
model_root_dir=self.cache_dir,
) )
) )
return session return session

21
machine-learning/test_main.py
View File

@ -1028,7 +1028,12 @@ class TestOcr:
text_recognizer.load() text_recognizer.load()
rapid_recognizer.assert_called_once_with( rapid_recognizer.assert_called_once_with(
OcrOptions(session=ort_session.return_value, rec_batch_num=6, rec_img_shape=(3, 48, 320)) OcrOptions(
session=ort_session.return_value,
rec_batch_num=6,
rec_img_shape=(3, 48, 320),
model_root_dir=text_recognizer.cache_dir,
)
) )
def test_set_custom_max_batch_size(self, ort_session: mock.Mock, path: mock.Mock, mocker: MockerFixture) -> None: def test_set_custom_max_batch_size(self, ort_session: mock.Mock, path: mock.Mock, mocker: MockerFixture) -> None:
@ -1041,7 +1046,12 @@ class TestOcr:
text_recognizer.load() text_recognizer.load()
rapid_recognizer.assert_called_once_with( rapid_recognizer.assert_called_once_with(
OcrOptions(session=ort_session.return_value, rec_batch_num=4, rec_img_shape=(3, 48, 320)) OcrOptions(
session=ort_session.return_value,
rec_batch_num=4,
rec_img_shape=(3, 48, 320),
model_root_dir=text_recognizer.cache_dir,
)
) )
def test_ignore_other_custom_max_batch_size( def test_ignore_other_custom_max_batch_size(
@ -1056,7 +1066,12 @@ class TestOcr:
text_recognizer.load() text_recognizer.load()
rapid_recognizer.assert_called_once_with( rapid_recognizer.assert_called_once_with(
OcrOptions(session=ort_session.return_value, rec_batch_num=6, rec_img_shape=(3, 48, 320)) OcrOptions(
session=ort_session.return_value,
rec_batch_num=6,
rec_img_shape=(3, 48, 320),
model_root_dir=text_recognizer.cache_dir,
)
) )