I have some issues during testing or model.eval() with ComplexBatchNorm2d (the training is fine). The problem line is:
input = input - mean[None, :, None, None]
The problem seems to be the shape difference between mean and input.
In this case, the mean shape is [1000, 64, 32, 32] and input shape is [64, 64].
Note that, I used VGG16 like model with CIFAR10 dataset.
With the same model, NaiveComplexBatchNorm2d is working fine.
Hello,
I have some issues during testing or
model.eval()
withComplexBatchNorm2d
(the training is fine). The problem line is:The problem seems to be the shape difference between mean and input. In this case, the mean shape is [1000, 64, 32, 32] and input shape is [64, 64]. Note that, I used VGG16 like model with CIFAR10 dataset.
With the same model,
NaiveComplexBatchNorm2d
is working fine.