You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, from the documentation of the library it is unclear whether the image variants of the loss function (e.g., AdaptiveImageLossFunction) expect images in NCHW or NHWC order. Furthermore, should the input value range be [0, 1] or [0, 255]?
The text was updated successfully, but these errors were encountered:
I guess it doesn't matter. The AdaptiveLossFunction only accepts rank-2 tensors, where the innermost dimension is the batch and the outermost dimension is the feature. All residual images must be flattened before feeding into the loss function.
Hello, from the documentation of the library it is unclear whether the image variants of the loss function (e.g.,
AdaptiveImageLossFunction
) expect images in NCHW or NHWC order. Furthermore, should the input value range be [0, 1] or [0, 255]?The text was updated successfully, but these errors were encountered: