search

modelscope / facechain

FaceChain is a deep-learning toolchain for generating your Digital-Twin.
Apache License 2.0
8.77k stars 820 forks source link

RuntimeError: nms_impl: implementation for device cuda:0 not found. #580

Closed lvsh2012 closed 1 day ago

lvsh2012 commented 3 weeks ago

gradio 正常启动了，但是在生成的时报错：RuntimeError: nms_impl: implementation for device cuda:0 not found.‘’

70 按照方式还是不行

(facechain) root@dl:/mnt/code/facechain# pip show mmcv-full Name: mmcv-full Version: 1.7.2 Summary: OpenMMLab Computer Vision Foundation Home-page: https://github.com/open-mmlab/mmcv Author: MMCV Contributors Author-email: openmmlab@gmail.com License: UNKNOWN Location: /mnt/conda/envs/facechain/lib/python3.8/site-packages Requires: addict, numpy, packaging, Pillow, pyyaml, yapf

(facechain) root@dl:/mnt/code/facechain# pip show torch Name: torch Version: 2.3.1 Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration Home-page: https://pytorch.org/ Author: PyTorch Team Author-email: packages@pytorch.org License: BSD-3 Location: /mnt/conda/envs/facechain/lib/python3.8/site-packages

You-Cun commented 2 weeks ago

There may be many reasons for such error. You can try the checking methods in https://blog.csdn.net/seven_hells/article/details/134864191 to ensure the version of PyTorch and CUDA.