Created by: lele012

the memory of my gpu is 6000M

my code like this:

from paddleocr import PaddleOCR, draw_ocr from PIL import Image import datetime import os

os.environ['FLAGS_eager_delete_tensor_gb'] = "0.0" os.environ['FLAGS_fraction_of_gpu_memory_to_use'] = "1.0"

模型路径下必须含有model和params文件

ocr = PaddleOCR(use_gpu=True, gpu_mem=4000, det_model_dir='D:\AI\ocr\models\ch_ppocr_server_v1.1_det_infer', rec_model_dir='D:\AI\ocr\models\ch_ppocr_server_v1.1_rec_infer', rec_char_dict_path='D:\AI\ocr\dicts\ppocr_keys_v1.txt', cls_model_dir='D:\AI\ocr\models\ch_ppocr_mobile_v1.1_cls_infer', use_angle_cls=True) img_path = 'D:\AI\ocr\images\1.jpg' start = datetime.datetime.now() result = ocr.ocr(img_path) for line in result: print(line) end = datetime.datetime.now() print("总耗时:", (end-start).seconds)

the error is :

ResourceExhaustedError:

Out of memory error on GPU 0. Cannot allocate 121.078369MB memory on GPU 0, available memory is only 55.625000MB.

Please check whether there is any other process using GPU 0.

1. If yes, please stop them, or start PaddlePaddle on another GPU.
2. If no, please try one of the following suggestions:
   1. Decrease the batch size of your model.
   2. FLAGS_fraction_of_gpu_memory_to_use is 0.50 now, please set it to a higher value but less than 1.0. The command is export FLAGS_fraction_of_gpu_memory_to_use=xxx.

at (D:\1.7.0\paddle\paddle\fluid\memory\detail\system_allocator.cc:151)