SSIMLoss result does not have gradient

[Can-Zhao]

Describe the bug
SSIMLoss result does not have gradient
@PedroFerreiradaCosta
@wyli

To Reproduce

import torch
from monai.losses.ssim_loss import SSIMLoss

x = torch.ones([1,1,10,10])/2
y = torch.ones([1,1,10,10])/2
y.requires_grad_(True)
data_range = x.max().unsqueeze(0)
loss = SSIMLoss(spatial_dims=2)(x,y,data_range)
print(loss.requires_grad)

Expected behavior
loss.requires_grad will be False. But it should be True

Screenshots
If applicable, add screenshots to help explain your problem.

Environment

Ensuring you use the relevant python executable, please paste the output of:

python -c 'import monai; monai.config.print_debug_info()'

Additional context
Add any other context about the problem here.

[wyli]

Thanks for reporting this. we'll release 1.1 soon, do you have time to fix it this week? @PedroFerreiradaCosta @Can-Zhao otherwise I'll revert #5550 early next week.

[Can-Zhao]

I'm not familiar with this script. If @PedroFerreiradaCosta does not have time, I was not sure if I could get it fixed this week. If we did not manage to fix it, we could revert it next week

[PedroFerreiradaCosta]

Thank you for the report @Can-Zhao ! I will try to fix this until the end of the week.

[Can-Zhao]

Thank you for the report @Can-Zhao ! I will try to fix this until the end of the week.

That's awesome! Thank you so much!!