Traceback (most recent call last):
File "/media/baize/0_code/mtl_main/main.py", line 112, in
main(params)
File "/media/baize/0_code/mtl_main/main.py", line 98, in main
NYUmodel.train(nyuv2_train_loader, nyuv2_test_loader, params.epochs)
File "/media/baize/0_code/mtl_main/LibMTL/trainer.py", line 230, in train
w = self.model.backward(train_losses, **self.kwargs['weight_args'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/media/baize/0_code/mtl_main/LibMTL/weighting/Aligned_MTL.py", line 25, in backward
lmbda, V = torch.symeig(M, eigenvectors=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/py311tourch201/lib/python3.11/site-packages/torch/_linalg_utils.py", line 136, in _symeig
raise RuntimeError(
RuntimeError: This function was deprecated since version 1.9 and is now removed. The default behavior has changed from using the upper triangular portion of the matrix by default to using the lower triangular portion.
L, _ = torch.symeig(A, upper=upper) should be replaced with:
L = torch.linalg.eigvalsh(A, UPLO='U' if upper else 'L')
and
L, V = torch.symeig(A, eigenvectors=True) should be replaced with:
L, V = torch.linalg.eigh(A, UPLO='U' if upper else 'L')
Traceback (most recent call last): File "/media/baize/0_code/mtl_main/main.py", line 112, in
main(params)
File "/media/baize/0_code/mtl_main/main.py", line 98, in main
NYUmodel.train(nyuv2_train_loader, nyuv2_test_loader, params.epochs)
File "/media/baize/0_code/mtl_main/LibMTL/trainer.py", line 230, in train
w = self.model.backward(train_losses, **self.kwargs['weight_args'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/media/baize/0_code/mtl_main/LibMTL/weighting/Aligned_MTL.py", line 25, in backward
lmbda, V = torch.symeig(M, eigenvectors=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/py311tourch201/lib/python3.11/site-packages/torch/_linalg_utils.py", line 136, in _symeig
raise RuntimeError(
RuntimeError: This function was deprecated since version 1.9 and is now removed. The default behavior has changed from using the upper triangular portion of the matrix by default to using the lower triangular portion.
L, _ = torch.symeig(A, upper=upper) should be replaced with: L = torch.linalg.eigvalsh(A, UPLO='U' if upper else 'L')
and
L, V = torch.symeig(A, eigenvectors=True) should be replaced with: L, V = torch.linalg.eigh(A, UPLO='U' if upper else 'L')