PaddlePaddle / FastDeploy

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.

Home Page:https://www.paddlepaddle.org.cn/fastdeploy

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

fastdeploy/fastdeploy_model.cc(239)::CreateCpuBackend Found no valid backend for model

lxiaoxiaoxing opened this issue · comments

Environment

FastDeploy version: e.g 1.0.7 or the latest code in develop branch
OS Platform: Linux x64
Hardware: CPU
Program Language: Python 3.8.10

Problem description

I first run: docker pull registry.baidubce.com/paddlepaddle/fastdeploy:1.0.7-cpu-only-21.10, it's my environment.
Then, I run it in python ,fastdeploy.vision.facedet.SCRFD('scrfd_500m_bnkps_shape640x640.onnx', runtime_option=None, model_format=ModelFormat.ONNX)
/usr/lib/python3/dist-packages/requests/init.py:89: RequestsDependencyWarning: urllib3 (2.0.2) or chardet (3.0.4) doesn't match a supported version!
warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
[ERROR] fastdeploy/fastdeploy_model.cc(239)::CreateCpuBackend Found no valid backend for model: scrfd
[ERROR] fastdeploy/vision/facedet/contrib/scrfd.cc(96)::Initialize Failed to initialize fastdeploy backend.
Traceback (most recent call last):
File "test01.py", line 29, in
model = fastdeploy.vision.facedet.SCRFD('scrfd_500m_bnkps_shape640x640.onnx', runtime_option=None, model_format=ModelFormat.ONNX)
File "/usr/local/lib/python3.8/dist-packages/fastdeploy/vision/facedet/contrib/scrfd.py", line 41, in init
assert self.initialized, "SCRFD initialize failed."
AssertionError: SCRFD initialize failed.

Solved, reinstalling fastdeploy