SoftmaxCrossEntropyLoss¶
Calculate a softmax cross-entropy loss between logit predictions (unnormalized log probabilities) and integer target labels or a label distribution.
Note that, when you train a neural network with this loss, you would not use a softmax activation function on the output layer, since this loss already includes the softmax transform. The predictions must have a (usually trailing) statistic axis of length equal to the number of classes. The labels can either be of the same shape as the predictions (or a broadcastable shape) if labels_are is set to 'distributions' (see labels_are parameter) or they can be encoded as integers (class indices) and in that case do not have a statistic axis. This is a multi-class loss; for a binary loss, see the SigmoidBinaryCrossEntropy node. Like all Loss nodes (except MeasureLoss), this node returns the per-example loss, which needs to be manually summed or averaged to get a total dataset/batch loss. This the canonical classification loss for the softmax activation function. For the sigmoid activation function, use the SigmoidBinaryCrossEntropy node. Version 1.1.0
Ports/Properties¶
preds¶
Predictions.
targs¶
Target values.
output¶
Output.
labels_are¶
Format of the labels. If 'integers', the labels are expected to be integer values between 0 and the number of classes minus 1. If 'distributions', the labels are expected to have a statistic axis of length equal to the number of classes, and the values are expected to be probabilities that sum to 1. In this case, labels can be a one-hot encoding, or a distribution corresponding to a soft labeling. If set to 'auto', then integers is inferred if the data is of integer type and distributions is inferred if the data is of same shape as the predictions or a broadcastable shape. Otherwise an error is raised.
sanity_checks¶
Perform sanity checks on the inputs.
set_breakpoint¶
Set a breakpoint on this node. If this is enabled, your debugger (if one is attached) will trigger a breakpoint.
metadata¶
User-definable meta-data associated with the node. Usually reserved for technical purposes.
axis_pairing¶
How to pair axes of the preds and targs operands. In 'positional' mode, axes are paired by their position according to a right alignment, that is, the last axis of the first operand is paired with the last axis of the second operand, and so on, while any missing axes behave as if they were unnamed axes of length 1 (this is the same way plain n-dimensional arrays pair in Python/numpy). In 'matched' mode, axes are paired by their type and optionally label, where the axis order of the first operand is preserved in the output, optionally with additional axes that only occur in the second operand prepended on the left. The other operand then has its axes reordered to match. All axis classes are treated as distinct, except for the plain axis, which is treated as a wildcard axis that can pair with any other axis. The 'default' value resolves to a value that may be overridden in special contexts (e.g., an ambient Inference node) and otherwise resolves to the setting of the configuration variable default_axis_pairing, which is set to 'positional' in 2024.x. See also the 'label_handling' property for how labels are treated in this mode. Note that axis pairing can be subtle, and it is recommended to not blindly trust that the default behavior is always what the user intended.
label_pairing¶
How to treat axis labels when pairing axes in 'matched' mode. In 'always' mode, labels are always considered significant, and axes with different labels are always considered distinct, which means that, if the two operands each have an axis of same type but with different labels, each operand will have a singleton axis inserted to pair with the respective axis in the other operand. In 'ignore' mode, labels are entirely ignored when pairing axes; this means that, if multiple axes of the same type occur in one or more operands, the last space axis in the first operand is paired with the last space axis in the second operand, etc. as in positional mode. In 'auto' mode, labels are only considered significant if they are necessary for distinguishing two or more axes of the same type in any of the operands, or if they occur on a plain axis.
lists_as_arrays¶
Whether to treat lists as numeric arrays, as opposed to a recursive data structure. This is equivalent to converting any list operand(s) to arrays before passing them to the node. Broadly, enabling this allows for more efficient processing of large lists of either numbers, or lists of many smaller arrays, with some limitations and caveats, as follows. If one operand was a list and the other an array, an array will be returned, and if all were lists, a list will be returned (if the operand lists themselves contained arrays, the result is still a "pure" list of potentially nested lists of numbers). A limitation is that input lists may contain ONLY numbers or arrays of the same shape (e..g., no lists of blocks or packets, dictionaries, or irregular array shapes in this mode). In contrast, when the option is disabled, then if one operand is a list and the other is not a list (e.g., a number, array, block, packet, etc), then each element of the list is separately undergoing the operation while the other operand is held fixed. This has the consequence that a) the result will generally be a list if at least one operand is a list and b) the result will be mathematically different when one is a list and the other is an array, because the array will be separately combined with each list element. Note the default for this option was enabled by default in NeuroPype 2023. The option can also be set globally or in a context using the WithOptions node, for example for pipeline-wide backwards compatibility.