search

cleardusk / 3DDFA_V2

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
MIT License
2.9k stars 514 forks source link

how to use onnxruntime-gpu？ #64

Open natgnah opened 3 years ago

natgnah commented 3 years ago

On window platform, CPU usage will be above 80%. So I want to change onnxruntime to onnxruntime-gpu

But I have the following problems： Traceback (most recent call last): File "demo_webcam_smooth.py", line 124, in main(args) File "demo_webcam_smooth.py", line 29, in main from FaceBoxes.FaceBoxes_ONNX import FaceBoxes_ONNX File "d:\Python\3DDFA_V2-master\FaceBoxes\FaceBoxes_ONNX.py", line 16, in import onnxruntime File "D:\anaconda3\envs\Vtuber\lib\site-packages\onnxruntime__init__.py", line 13, in from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, set_seed, \ ImportError: cannot import name 'get_all_providers' from 'onnxruntime.capi._pybind_state'

Can anyone point me in the direction of using onnxruntime-gpu?

cyjouc commented 3 years ago

Hi, when i run demo.py ,the error :Error in `python': double free or corruption (out): ?do you occur to the problem?

cleardusk commented 3 years ago

This repo is not tested for onnxruntime-gpu, so there may be some workloads to implement it but the code change maybe small. Sorry for that I have no time for this feature now. BTW, welcome for related PRs : )

cyjouc commented 3 years ago

TKS for your help. when I not use the onnx, python demo.py -f examples/inputs/emma.jpg Error in `python': munmap_chunk(): invalid pointer: 0x00007f7a39596ce0 ? would you like help me solve the error? TKS very much