guided-diffusion
guided-diffusion copied to clipboard
evaluation errors
When doing the evaluation, the following error accurs:
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) INVALID_ARGUMENT: activation input is not finite. : Tensor had NaN values [[{{node 2905231348_876199450/conv_2/CheckNumerics}}]]
[[strided_slice_2/_5]]
(1) INVALID_ARGUMENT: activation input is not finite. : Tensor had NaN values
[[{{node 2905231348_876199450/conv_2/CheckNumerics}}]]
0 successful operations.
0 derived errors ignored.
How to fix this problem? Thanks.
I meet the same problem. Do you fix it?
I have the same issue.
I'm using the Imagenet dataset -
Reference batch: VIRTUAL_imagenet256_labeled.npz Sample batch: admnet_imagenet256.npz
Error:
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: activation input is not finite. : Tensor had NaN values [[node 2559280021_1452120685/conv_2/CheckNumerics (defined at ..) [[strided_slice_2/_5]]
(1) Invalid argument: activation input is not finite. : Tensor had NaN values [[node 2559280021_1452120685/conv_2/CheckNumerics (defined at ..)
Have you fix? I have the same issue.
I have the same issue.
I'm using the Imagenet dataset -
Reference batch: VIRTUAL_imagenet256_labeled.npz Sample batch: admnet_imagenet256.npz
Error:
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: activation input is not finite. : Tensor had NaN values [[node 2559280021_1452120685/conv_2/CheckNumerics (defined at ..) [[strided_slice_2/_5]]
(1) Invalid argument: activation input is not finite. : Tensor had NaN values [[node 2559280021_1452120685/conv_2/CheckNumerics (defined at ..)
Anyone solved the problem?
same problem