Paddlex安装hpi以后调用PP_StructureV3报错

[snow-swallow]

trafficstars

Checklist:

• [X] 查找历史相关issue寻求解答
• [X] 翻阅FAQ
• [X] 翻阅PaddleX 文档
• [X] 确认bug是否在新版本里还未修复

描述问题

1. 使用docker镜像部署在ks中

镜像信息：

[paddle:3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6](http://ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddle:3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6)

显卡信息

Fri Jun 13 02:52:02 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.230.02             Driver Version: 535.230.02   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| 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  NVIDIA A40                     Off | 00000000:AF:00.0 Off |                    0 |
|  0%   41C    P0              78W / 300W |   6397MiB / 46068MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
+---------------------------------------------------------------------------------------+

2. 版面分析执行的命令:

paddlex --pipeline  PP-StructureV3  --input   https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/demo_paper.png --use_hpip

3. 报错

File "/root/PaddleX/paddlex/inference/models/image_classsification/predictor.py", line 49, in _ init
self.preprocessors, self.infer, self.postprocessors= self._build()
File "/root/PaddleX/paddlex/inference/models/image_classification/predictor.py",line 82, in _build
infer= self.create_static_infer()
/return HPInfer(
File "/root/Paddlex/paddlex/inference/models/base/predictor/base_predictorin create_static_infer
File "/root/PaddleX/paddlex/utils/deps.py", line 148, in _ rapper
return old_init_func(self, *args, **kwargs)
File "/root/PaddleX/paddlex/inference/models/common/static_iinfer.py",line 575, in in init_
File "/root/PaddleX/paddlex/inference/models/common/static_infer.py", line 630, in _determine_backend_config
backend, backend_config = self._determine_backend_and_config()
raise RuntimeError(
RuntimeError: No inference backend and confiauration could be suggested, Reason: "PP-LCNJet x1 0 textline ori' is not a known model.