fix: add PaddlePaddle 2.x/3.x API compatibility layer

PaddlePaddle 3.0.0b2 has "Illegal instruction" error on current CPU.
Downgrade to stable 2.6.2 which works but uses different API.

Changes:
- Auto-detect PaddlePaddle version at runtime
- Use 'device' parameter for 3.x (device="gpu:0" or "cpu")
- Use 'use_gpu' + 'gpu_mem' parameters for 2.x
- Apply to both get_ocr_engine() and get_structure_engine()
- Log PaddlePaddle version in initialization messages

Current setup:
- paddlepaddle-gpu==2.6.2 (stable, CUDA compiled)
- paddleocr==3.3.1
- paddlex==3.3.9

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-11-14 10:56:29 +08:00
parent 36944117f4
commit 80c091b89a

View File

@@ -170,25 +170,48 @@ class OCRService:
logger.info(f"Initializing PaddleOCR engine for language: {lang} (GPU: {self.use_gpu})")
try:
# PaddleOCR 3.x uses 'device' parameter instead of 'use_gpu' and 'gpu_mem'
device = f"gpu:{settings.gpu_device_id}" if self.use_gpu else "cpu"
self.ocr_engines[lang] = PaddleOCR(
use_angle_cls=True,
lang=lang,
device=device,
)
logger.info(f"PaddleOCR engine ready for {lang} ({'GPU' if self.use_gpu else 'CPU'} mode)")
# Check PaddlePaddle version to use correct API
paddle_version = paddle.__version__
is_paddle_3x = paddle_version.startswith('3.')
if is_paddle_3x:
# PaddlePaddle 3.x uses 'device' parameter
device = f"gpu:{settings.gpu_device_id}" if self.use_gpu else "cpu"
self.ocr_engines[lang] = PaddleOCR(
use_angle_cls=True,
lang=lang,
device=device,
)
else:
# PaddlePaddle 2.x uses 'use_gpu' and 'gpu_mem' parameters
self.ocr_engines[lang] = PaddleOCR(
use_angle_cls=True,
lang=lang,
use_gpu=self.use_gpu,
gpu_mem=int(settings.gpu_memory_fraction * 1000) if self.use_gpu else 500,
)
logger.info(f"PaddleOCR engine ready for {lang} (PaddlePaddle {paddle_version}, {'GPU' if self.use_gpu else 'CPU'} mode)")
except Exception as e:
# If GPU initialization fails, fall back to CPU
if self.use_gpu:
logger.warning(f"GPU initialization failed, falling back to CPU: {e}")
self.use_gpu = False
self.ocr_engines[lang] = PaddleOCR(
use_angle_cls=True,
lang=lang,
device="cpu",
)
paddle_version = paddle.__version__
is_paddle_3x = paddle_version.startswith('3.')
if is_paddle_3x:
self.ocr_engines[lang] = PaddleOCR(
use_angle_cls=True,
lang=lang,
device="cpu",
)
else:
self.ocr_engines[lang] = PaddleOCR(
use_angle_cls=True,
lang=lang,
use_gpu=False,
)
logger.info(f"PaddleOCR engine ready for {lang} (CPU mode - fallback)")
else:
raise
@@ -206,23 +229,13 @@ class OCRService:
logger.info(f"Initializing PP-StructureV3 engine (GPU: {self.use_gpu})")
try:
# PaddleOCR 3.x uses 'device' parameter instead of 'use_gpu' and 'gpu_mem'
device = f"gpu:{settings.gpu_device_id}" if self.use_gpu else "cpu"
self.structure_engine = PPStructureV3(
use_doc_orientation_classify=False,
use_doc_unwarping=False,
use_textline_orientation=False,
use_table_recognition=True,
use_formula_recognition=True,
layout_threshold=0.5,
device=device,
)
logger.info(f"PP-StructureV3 engine ready ({'GPU' if self.use_gpu else 'CPU'} mode)")
# Check PaddlePaddle version to use correct API
paddle_version = paddle.__version__
is_paddle_3x = paddle_version.startswith('3.')
except Exception as e:
# If GPU initialization fails, fall back to CPU
if self.use_gpu:
logger.warning(f"GPU initialization failed for PP-Structure, falling back to CPU: {e}")
if is_paddle_3x:
# PaddlePaddle 3.x uses 'device' parameter
device = f"gpu:{settings.gpu_device_id}" if self.use_gpu else "cpu"
self.structure_engine = PPStructureV3(
use_doc_orientation_classify=False,
use_doc_unwarping=False,
@@ -230,8 +243,49 @@ class OCRService:
use_table_recognition=True,
use_formula_recognition=True,
layout_threshold=0.5,
device="cpu",
device=device,
)
else:
# PaddlePaddle 2.x uses 'use_gpu' and 'gpu_mem' parameters
self.structure_engine = PPStructureV3(
use_doc_orientation_classify=False,
use_doc_unwarping=False,
use_textline_orientation=False,
use_table_recognition=True,
use_formula_recognition=True,
layout_threshold=0.5,
use_gpu=self.use_gpu,
gpu_mem=int(settings.gpu_memory_fraction * 1000) if self.use_gpu else 500,
)
logger.info(f"PP-StructureV3 engine ready (PaddlePaddle {paddle_version}, {'GPU' if self.use_gpu else 'CPU'} mode)")
except Exception as e:
# If GPU initialization fails, fall back to CPU
if self.use_gpu:
logger.warning(f"GPU initialization failed for PP-Structure, falling back to CPU: {e}")
paddle_version = paddle.__version__
is_paddle_3x = paddle_version.startswith('3.')
if is_paddle_3x:
self.structure_engine = PPStructureV3(
use_doc_orientation_classify=False,
use_doc_unwarping=False,
use_textline_orientation=False,
use_table_recognition=True,
use_formula_recognition=True,
layout_threshold=0.5,
device="cpu",
)
else:
self.structure_engine = PPStructureV3(
use_doc_orientation_classify=False,
use_doc_unwarping=False,
use_textline_orientation=False,
use_table_recognition=True,
use_formula_recognition=True,
layout_threshold=0.5,
use_gpu=False,
)
logger.info("PP-StructureV3 engine ready (CPU mode - fallback)")
else:
raise