Package qupath.bioimageio.spec.tensor
Class Processing.ProcessingWithMode
java.lang.Object
qupath.bioimageio.spec.tensor.Processing
qupath.bioimageio.spec.tensor.Processing.ProcessingWithMode
- Direct Known Subclasses:
Processing.ScaleMeanVariance,Processing.ScaleRange,Processing.ZeroMeanUnitVariance
- Enclosing class:
- Processing
A processing mode that operates optionally on different sets of data.
For example, per_dataset or per_sample.
-
Nested Class Summary
Nested classes/interfaces inherited from class qupath.bioimageio.spec.tensor.Processing
Processing.Binarize, Processing.Clip, Processing.ProcessingMode, Processing.ProcessingWithMode, Processing.ScaleLinear, Processing.ScaleMeanVariance, Processing.ScaleRange, Processing.Sigmoid, Processing.ZeroMeanUnitVariance -
Method Summary
Methods inherited from class qupath.bioimageio.spec.tensor.Processing
getDeserializers, getKwargs, getName
-
Method Details
-
getEps
public double getEps()Epsilon for numeric stability: out = (tensor - mean) / (std + eps) * (ref_std + eps) + ref_mean.- Returns:
- The epsilon value.
-
getMode
Mode for computing processing. Not all are supported for all operations, but here are some options: | mode | description | | ----------- | ------------------------------------ | | fixed | Fixed values | | per_dataset | Compute for the entire dataset | | per_sample | Compute for each sample individually | -
getAxes
The subset of axes to scale jointly. For example xy to normalize the two image axes for 2d data jointly. Default: scale all non-batch axes jointly.- Returns:
- the subset of axes to scale jointly.
-