The following error occurred while running the superpoin code:
Error 1
UserWarning: Default grid_Sample and after_Grid behavior has changed to align_Corners; False since 1.3.0 Please specify align_Corners; True if the old behavior is desired See the documentation of grid_Sample for details
" Default grid_Sample and after_Grid behavior has changed"
Translation: User warning: Since 1.3.0, the default grid_Sample and after_Grid behavior has been changed to align_Carners; False. If old behavior is required, please specify align_Carners; True. For detailed information, please refer to grid_The document for the sample
"The default grid_sample and affine_grid behaviors have been changed"
**Solution: * * Find D: Anaconda envs pytorch lib site packages torch nn functionalitypy, open it, and align line 4095_Corners: Optional [bool]= Change None to align_Corners: Optional [bool]= True, line 4238 reads= Align_Corners: Optional [bool]= Change None to align_Corners: Optional [bool]= True
Error 2
Error # 15: Initializing libiomp5md0ll, but found libiomp5md0ll 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/.
Translation: Error # 15: Initializing libomp5mD.DLL, but found that libomp5mD.DLL has already been initialized
OMP: This indicates that multiple copies of the OpenMP runtime have been linked to the program. This is dangerous as it may reduce performance or lead to incorrect results. The best practice is to ensure that only one OpenMP runtime is linked to the process, such as avoiding static linking of OpenMP runtime libraries in any library. As an unsafe, unsupported, and undocumented solution, you can set the environment variable KMP_DUPLICATE_LIB_OK= True is set to allow the program to continue executing, but this may cause crashes or silently produce incorrect results. For more information, please refer to http://www.intel.com/software/products/support/.
Solution
Add the following code before the file:
import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'
This method is relatively simple, but it is not a one-time solution. Searching blogs reveals that there are two other methods. I personally think adding two lines of code is the simplest
Reference Blog.