Thanks for your error report and we appreciate it a lot.
- I have searched related issues but cannot get the expected help.
- The bug has not been fixed in the latest version.
(openmmlab) D:\Desktop\openmmlab\mmsegmentation>python demo/image_demo.py demo/demo.png configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth --device cuda:0 --out-file result.jpg
Traceback (most recent call last):
File "demo/image_demo.py", line 6, in
from mmseg.apis import inference_model, init_model, show_result_pyplot
File "d:\desktop\openmmlab\mmsegmentation\mmseg\apis_init_.py", line 2, in
from .inference import inference_model, init_model, show_result_pyplot
File "d:\desktop\openmmlab\mmsegmentation\mmseg\apis\inference.py", line 14, in
from mmseg.models import BaseSegmentor
File "d:\desktop\openmmlab\mmsegmentation\mmseg\models_init_.py", line 3, in
from .backbones import * # noqa: F401,F403
File "d:\desktop\openmmlab\mmsegmentation\mmseg\models\backbones_init_.py", line 2, in
from .beit import BEiT
File "d:\desktop\openmmlab\mmsegmentation\mmseg\models\backbones\beit.py", line 19, in
from ..utils import PatchEmbed
File "d:\desktop\openmmlab\mmsegmentation\mmseg\models\utils_init_.py", line 2, in
from .basic_block import BasicBlock, Bottleneck
File "d:\desktop\openmmlab\mmsegmentation\mmseg\models\utils\basic_block.py", line 10, in
from mmseg.utils import OptConfigType
File "d:\desktop\openmmlab\mmsegmentation\mmseg\utils_init_.py", line 24, in
from .mask_classification import MatchMasks, seg_data_to_instance_data
File "d:\desktop\openmmlab\mmsegmentation\mmseg\utils\mask_classification.py", line 5, in
from mmcv.ops import point_sample
File "D:\Anaconda3\envs\openmmlab\lib\site-packages\mmcv\ops_init_.py", line 3, in
from .active_rotated_filter import active_rotated_filter
File "D:\Anaconda3\envs\openmmlab\lib\site-packages\mmcv\ops\active_rotated_filter.py", line 10, in
ext_module = ext_loader.load_ext(
File "D:\Anaconda3\envs\openmmlab\lib\site-packages\mmcv\utils\ext_loader.py", line 13, in load_ext
ext = importlib.import_module('mmcv.' + name)
File "D:\Anaconda3\envs\openmmlab\lib\importlib_init_.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
ImportError: DLL load failed while importing _ext: 找不到指定的程序。
It seems that mmcv may not have been installed correctly. As of today, there is still no compiled version of mmcv for PyTorch 2.2. A possible solution is to install a version of PyTorch below 2.1.2 and then reinstall following the official process for mmseg.
open-mmlab
