Eine Frage haben? Verbinden Sie sich mit der Community im TensorFlow Forum

# tf.math.l2_normalize

Normalizes along dimension `axis` using an L2 norm. (deprecated arguments)

For a 1-D tensor with `axis = 0`, computes

``````output = x / sqrt(max(sum(x**2), epsilon))
``````

For `x` with more dimensions, independently normalizes each 1-D slice along dimension `axis`.

`x` A `Tensor`.
`axis` Dimension along which to normalize. A scalar or a vector of integers.
`epsilon` A lower bound value for the norm. Will use `sqrt(epsilon)` as the divisor if `norm < sqrt(epsilon)`.
`name` A name for this operation (optional).
`dim` Deprecated alias for axis.

A `Tensor` with the same shape as `x`.

[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"Benötigte Informationen nicht gefunden" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"Zu umständlich/zu viele Schritte" },{ "type": "thumb-down", "id": "outOfDate", "label":"Nicht mehr aktuell" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Samples / code issue" },{ "type": "thumb-down", "id": "otherDown", "label":"Sonstiges" }]
[{ "type": "thumb-up", "id": "easyToUnderstand", "label":"Leicht verständlich" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"Mein Problem wurde gelöst" },{ "type": "thumb-up", "id": "otherUp", "label":"Sonstiges" }]