RuntimeError: aclnnMaxPool2d or aclnnMaxPool2dGetWorkspaceSize not in libopapi.so

一、问题现象（附报错日志上下文）：
xxxx

二、软件版本:
-- CANN 版本 :  8.0.RC3
--Pytorch 版本: 2.1.0
--Python 版本 :python3.8
--操作系统版本 :ubuntu20.04

三、测试步骤：
bash ./tools/dist_train.sh ./projects/configs/maptr/maptr_tiny_r50_24e_bevformer.py 8

四、日志信息:
Traceback (most recent call last):
  File "./tools/train.py", line 265, in <module>
    main()
  File "./tools/train.py", line 254, in main
    custom_train_model(
  File "/work/share/zyj/mxDriving/model_examples/MapTR/projects/mmdet3d_plugin/bevformer/apis/train.py", line 27, in custom_train_model
    custom_train_detector(
  File "/work/share/zyj/mxDriving/model_examples/MapTR/projects/mmdet3d_plugin/bevformer/apis/mmdet_train.py", line 199, in custom_train_detector
    runner.run(data_loaders, cfg.workflow)
  File "/mmcv/mmcv/runner/epoch_based_runner.py", line 136, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/mmcv/mmcv/runner/epoch_based_runner.py", line 53, in train
    self.run_iter(data_batch, train_mode=True, **kwargs)
  File "/mmcv/mmcv/runner/epoch_based_runner.py", line 31, in run_iter
    outputs = self.model.train_step(data_batch, self.optimizer,
  File "/mmcv/mmcv/parallel/distributed.py", line 63, in train_step
    output = self.module.train_step(*inputs[0], **kwargs[0])
  File "/usr/local/lib/python3.8/dist-packages/mmdet/models/detectors/base.py", line 237, in train_step
    losses = self(**data)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/work/share/zyj/mxDriving/model_examples/MapTR/projects/mmdet3d_plugin/maptr/detectors/maptr.py", line 162, in forward
    return self.forward_train(**kwargs)
  File "/mmcv/mmcv/runner/fp16_utils.py", line 236, in new_func
    output = old_func(*new_args, **new_kwargs)
  File "/work/share/zyj/mxDriving/model_examples/MapTR/projects/mmdet3d_plugin/maptr/detectors/maptr.py", line 278, in forward_train
    img_feats = self.extract_feat(img=img, img_metas=img_metas)
  File "/mmcv/mmcv/runner/fp16_utils.py", line 149, in new_func
    output = old_func(*new_args, **new_kwargs)
  File "/work/share/zyj/mxDriving/model_examples/MapTR/projects/mmdet3d_plugin/maptr/detectors/maptr.py", line 113, in extract_feat
    img_feats = self.extract_img_feat(img, img_metas, len_queue=len_queue)
  File "/work/share/zyj/mxDriving/model_examples/MapTR/projects/mmdet3d_plugin/maptr/detectors/maptr.py", line 92, in extract_img_feat
    img_feats = self.img_backbone(img)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/mmdet/models/backbones/resnet.py", line 642, in forward
    x = npu_max_pool2d(x, 3, 2, 1) #3
  File "/usr/local/lib/python3.8/dist-packages/torch/autograd/function.py", line 539, in apply
    return super().apply(*args, **kwargs)  # type: ignore[misc]
  File "/usr/local/lib/python3.8/dist-packages/mx_driving/fused/ops/npu_max_pool2d.py", line 17, in forward
    y = ads_c.npu_max_pool2d(x, kernel_size, stride, padding)
RuntimeError: aclnnMaxPool2d or aclnnMaxPool2dGetWorkspaceSize not in libopapi.so, or libopapi.sonot found.

GVP Ascend/DrivingSDK
暂停

内容风险标识

评论 (2)

GVPAscend/DrivingSDK暂停

内容风险标识