Skip to content

GitLab

"git@developer.sourcefind.cn:chenpangpang/transformers.git" did not exist on "33bca5419c0e08b7b9e58d26a57ececcda0c9fa9"
Unverified Commit e8efaecb authored by NielsRogge's avatar NielsRogge Committed by GitHub
Browse files

Move dependency to call method (#15941)

parent 5c6f57ee
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 2 deletions
src/transformers/models/layoutlmv2/feature_extraction_layoutlmv2.py
View file @ e8efaecb
...@@ -120,8 +120,6 @@ class LayoutLMv2FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM ...@@ -120,8 +120,6 @@ class LayoutLMv2FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
self.resample = resample self.resample = resample
self.apply_ocr = apply_ocr self.apply_ocr = apply_ocr
self.ocr_lang = ocr_lang self.ocr_lang = ocr_lang
if apply_ocr:
requires_backends(self, "pytesseract")
def __call__( def __call__(
self, images: ImageInput, return_tensors: Optional[Union[str, TensorType]] = None, **kwargs self, images: ImageInput, return_tensors: Optional[Union[str, TensorType]] = None, **kwargs
...@@ -200,6 +198,7 @@ class LayoutLMv2FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM ...@@ -200,6 +198,7 @@ class LayoutLMv2FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
# Tesseract OCR to get words + normalized bounding boxes # Tesseract OCR to get words + normalized bounding boxes
if self.apply_ocr: if self.apply_ocr:
requires_backends(self, "pytesseract")
words_batch = [] words_batch = []
boxes_batch = [] boxes_batch = []
for image in images: for image in images:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment