PaddleOCR
PaddleOCR copied to clipboard
PaddlePaddle
使用inference模型进行推理，如何使用多个gpu
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
-
系统环境/System Environment：ubuntu18.04 python3.7.0
-
版本号/Version：Paddle： paddlepaddle-gpu=2.4.0rc0 PaddleOCR：2.6 Paddlenlp: 2.4.1
-
运行指令/Command Code： from pprint import pprint from paddlenlp import Taskflow docprompt = Taskflow("document_intelligence") pprint(docprompt([{"doc": "1.jpg", "prompt": ["发票代码是多少?"]}]))
-
完整报错/Complete Error Message： 看到tools/infer/utility.py中代码： 223行：config.enable_use_gpu(args.gpu_mem, 0)设置是使用一个gpu，id是0，能不能设置使用多个gpu进行推理
可以看到只使用了0号卡 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 450.102.04 Driver Version: 450.102.04 CUDA Version: 11.0 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 GeForce RTX 208... Off | 00000000:5A:00.0 Off | N/A | | 16% 35C P8 19W / 250W | 2586MiB / 11019MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 1 GeForce RTX 208... Off | 00000000:66:00.0 Off | N/A | | 16% 29C P8 21W / 250W | 3MiB / 11019MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 2 GeForce RTX 208... Off | 00000000:BD:00.0 Off | N/A | | 16% 36C P8 18W / 250W | 3MiB / 11019MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 3 GeForce RTX 208... Off | 00000000:C1:00.0 Off | N/A | | 16% 33C P8 11W / 250W | 3MiB / 11019MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 60920 C python 2583MiB | +-----------------------------------------------------------------------------+
