解决 YOLO训练中mkl-service 与 libgomp.so.1 不兼容错误

在利用Ultralytics训练RT-DETR时，报错：

Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library.
        Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it.
Traceback (most recent call last):
  File "/data/ctc/yolov11/train.py", line 11, in <module>
    model.train(data=r"/data/ctc/yolov11/data.yaml",
  File "/data/ctc/yolov11/ultralytics/engine/model.py", line 802, in train
    self.trainer.train()
  File "/data/ctc/yolov11/ultralytics/engine/trainer.py", line 202, in train
    raise e
  File "/data/ctc/yolov11/ultralytics/engine/trainer.py", line 200, in train
    subprocess.run(cmd, check=True)
  File "/home/ctc/anaconda3/envs/yolov11/lib/python3.10/subprocess.py", line 526, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['/home/ctc/anaconda3/envs/yolov11/bin/python', '-m', 'torch.distributed.run', '--nproc_per_node', '4', '--master_port', '53639', '/home/ctc/.config/Ultralytics/DDP/_temp_g8tp5gwv140700465996528.py']' returned non-zero exit status 1.

解决方案：

在命令行执行设置环境变量：

export MKL_THREADING_LAYER=GNU

问题解决！