2. RuntimeError-OMP: Error #15:

[Tamer-Saleh]

OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized. OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.

• The first solution is to add the below two lines to the front of the train.py code; But it doesn't solve the problem fundamentally.
  import os
  os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"

• The second solution is to search for libiomp5md.dll in your conda environment; you can found two files in the directory libiomp5md.dll like this;
  "C:\ProgramData\Anaconda3\envs\changedetection\Lib\site-packages\torch\lib\libiomp5md.dll"
  "C:\ProgramData\Anaconda3\envs\changedetection\Library\bin\libiomp5md.dll"

• Keep on the second path and take cut the first path in another place or rename it, the problem is perfectly solved.