ValueError: numpy.ndarray size changed, may indicate binary incompatibility

[jieruyao49]

When I run the code train.py The error code is as follows:

Traceback (most recent call last):
  File "/home/code/RDSNet-master/tools/train.py", line 9, in <module>
    from mmdet.apis import (get_root_logger, init_dist, set_random_seed,
  File "/home/code/RDSNet-master/mmdet/apis/__init__.py", line 2, in <module>
    from .inference import (inference_detector, init_detector, show_result,
  File "/home/code/RDSNet-master/mmdet/apis/inference.py", line 11, in <module>
    from mmdet.core import get_classes
  File "/home/code/RDSNet-master/mmdet/core/__init__.py", line 6, in <module>
    from .post_processing import *  # noqa: F401, F403
  File "/home/code/RDSNet-master/mmdet/core/post_processing/__init__.py", line 1, in <module>
    from .bbox_nms import multiclass_nms, multiclass_nms_with_extra
  File "/home/code/RDSNet-master/mmdet/core/post_processing/bbox_nms.py", line 3, in <module>
    from mmdet.ops.nms import nms_wrapper
  File "/home/code/RDSNet-master/mmdet/ops/__init__.py", line 7, in <module>
    from .nms import nms, soft_nms
  File "/home/code/RDSNet-master/mmdet/ops/nms/__init__.py", line 1, in <module>
    from .nms_wrapper import nms, soft_nms
  File "/home/code/RDSNet-master/mmdet/ops/nms/nms_wrapper.py", line 4, in <module>
    from . import nms_cpu, nms_cuda
ImportError: libtorch_cpu.so: cannot open shared object file: No such file or directory
Traceback (most recent call last):
  File "/home/code/RDSNet-master/tools/train.py", line 9, in <module>
    from mmdet.apis import (get_root_logger, init_dist, set_random_seed,
  File "/home/code/RDSNet-master/mmdet/apis/__init__.py", line 2, in <module>
    from .inference import (inference_detector, init_detector, show_result,
  File "/home/code/RDSNet-master/mmdet/apis/inference.py", line 11, in <module>
    from mmdet.core import get_classes
  File "/home/code/RDSNet-master/mmdet/core/__init__.py", line 6, in <module>
    from .post_processing import *  # noqa: F401, F403
  File "/home/code/RDSNet-master/mmdet/core/post_processing/__init__.py", line 1, in <module>
    from .bbox_nms import multiclass_nms, multiclass_nms_with_extra
  File "/home/code/RDSNet-master/mmdet/core/post_processing/bbox_nms.py", line 3, in <module>
    from mmdet.ops.nms import nms_wrapper
  File "/home/code/RDSNet-master/mmdet/ops/__init__.py", line 7, in <module>
    from .nms import nms, soft_nms
  File "/home/code/RDSNet-master/mmdet/ops/nms/__init__.py", line 1, in <module>
    from .nms_wrapper import nms, soft_nms
  File "/home/code/RDSNet-master/mmdet/ops/nms/nms_wrapper.py", line 4, in <module>
    from . import nms_cpu, nms_cuda
ImportError: libtorch_cpu.so: cannot open shared object file: No such file or directory
Traceback (most recent call last):
  File "/home/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 246, in <module>
    main()
  File "/home/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 242, in main
    cmd=cmd)
subprocess.CalledProcessError: Command '['/home/anaconda3/envs/open-mmlab/bin/python3.7', '-u', '/home/code/RDSNet-master/tools/train.py', '--local_rank=1']' returned non-zero exit status 1.

My package is as follows: python 3.7 cudatoolkit 10.0.130 numpy 1.20.2 pytorch 1.2.0 torchvision 0.4.0