search

PaddlePaddle / PaddleHub

Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)
https://www.paddlepaddle.org.cn/hub
Apache License 2.0
12.67k stars 2.07k forks source link

运行gpu的demo 出错。 #1445

Open bbhxwl opened 3 years ago

bbhxwl commented 3 years ago

https://www.paddlepaddle.org.cn/hubdetail?name=chinese_ocr_db_crnn_server&en_category=TextRecognition 按照这个教程写的代码。代码我改成gpu的了。 import paddlehub as hub import cv2 ocr = hub.Module(name="chinese_ocr_db_crnn_mobile") result = ocr.recognize_text(images=[cv2.imread(r'C:\Users\bin\Desktop\temp\jpg')],use_gpu=True) print(result) 环境如下

image 异常如下。 image

bbhxwl commented 3 years ago

路径写错了。不过路径写对了以后，就是下面的错误了。GPU从来没成功过。 image

haoyuying commented 3 years ago

请问您使用的paddle版本是什么呢，建议使用paddle2.1版本