🔎 Search before asking

• I have searched the PaddleOCR Docs and found no similar bug report.
• I have searched the PaddleOCR Issues and found no similar bug report.
• I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

请问NVIDIA H20显卡 算力9.0 现在是还不支持吗 使用paddleocr 3.1.0 paddlepaddle-gpu 3.1.0 paddlex 3.1.3 进行测试，GPU输出结果为空

🏃‍♂️ Environment (运行环境)

paddleocr 3.1.0 paddlepaddle-gpu 3.1.0 paddlex 3.1.3

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

from paddleocr import PaddleOCR

初始化 PaddleOCR 实例

#ocr = PaddleOCR(

use_doc_orientation_classify=False,

use_doc_unwarping=False,

use_textline_orientation=False)

''' ocr = PaddleOCR( text_detection_model_name="PP-OCRv5_server_det", text_detection_model_dir="/home/ocr_projects/official_models/PP-OCRv5_server_det", text_recognition_model_name="PP-OCRv5_server_rec", text_recognition_model_dir="/home/ocr_projects/official_models/PP-OCRv5_server_rec", use_doc_orientation_classify=False, use_doc_unwarping=False, use_textline_orientation=False, device='gpu:3' ) # 更换 PP-OCRv5_server 模型

''' ocr = PaddleOCR(ocr_version="PP-OCRv4")

对示例图像执行 OCR 推理

result = ocr.predict( input="/test_img.jpg") print(result)

可视化结果并保存 json 结果

for res in result: res.print() res.save_to_img("output") res.save_to_json("output")