SparseFillEmptyRowsGrad
Zadbaj o dobrą organizację dzięki kolekcji
Zapisuj i kategoryzuj treści zgodnie ze swoimi preferencjami.
Gradient SparseFillEmptyRows.
Pobiera wektory Reverse_index_map o kształcie „[N]” i grad_values o kształcie „[N_full]”, gdzie „N_full >= N” i kopiuje dane do „d_values” lub „d_default_value”. Tutaj „wartości_d” mają kształt „[N]”, a „wartość_d_domyślna” jest skalarem.
d_values[j] = grad_values[reverse_index_map[j]] d_default_value = sum_{k : 0 .. N_full - 1} ( grad_values[k] * 1{k nie w Reverse_index_map})
Stałe
| Strunowy | OP_NAME | Nazwa tej operacji znana silnikowi rdzenia TensorFlow |
Metody dziedziczone
Z klasy java.lang.Object | wartość logiczna | równa się (Obiekt arg0) |
| ostatnia klasa<?> | pobierzKlasę () |
| wew | hashCode () |
| ostateczna pustka | powiadomić () |
| ostateczna pustka | powiadom wszystkich () |
| Strunowy | doString () |
| ostateczna pustka | czekaj (długi arg0, int arg1) |
| ostateczna pustka | czekaj (długi arg0) |
| ostateczna pustka | Czekać () |
Stałe
publiczny statyczny końcowy ciąg znaków OP_NAME
Nazwa tej operacji znana silnikowi rdzenia TensorFlow
Wartość stała: „SparseFillEmptyRowsGrad”
Metody publiczne
Metoda fabryczna służąca do tworzenia klasy opakowującej nową operację SparseFillEmptyRowsGrad.
Parametry
| zakres | aktualny zakres |
|---|
| odwrotna mapa indeksu | 1-D. Odwrotna mapa indeksu z SparseFillEmptyRows. |
|---|
| gradWartości | 1-D. Gradienty z podpory. |
|---|
Zwroty
- nowa instancja SparseFillEmptyRowsGrad
publiczne wyjście <T> dDefaultValue ()
0-D. Podpórka do wartości domyślnej.
publiczne wyjście <T> dValues ()
1-D. Podpora na wartości.
O ile nie stwierdzono inaczej, treść tej strony jest objęta licencją Creative Commons – uznanie autorstwa 4.0, a fragmenty kodu są dostępne na licencji Apache 2.0. Szczegółowe informacje na ten temat zawierają zasady dotyczące witryny Google Developers. Java jest zastrzeżonym znakiem towarowym firmy Oracle i jej podmiotów stowarzyszonych.
Ostatnia aktualizacja: 2025-07-26 UTC.
[null,null,["Ostatnia aktualizacja: 2025-07-26 UTC."],[],[],null,["# SparseFillEmptyRowsGrad\n\npublic final class **SparseFillEmptyRowsGrad** \nThe gradient of SparseFillEmptyRows.\n\n\nTakes vectors reverse_index_map, shaped \\`\\[N\\]\\`, and grad_values,\nshaped \\`\\[N_full\\]\\`, where \\`N_full \\\u003e= N\\` and copies data into either\n\\`d_values\\` or \\`d_default_value\\`. Here \\`d_values\\` is shaped \\`\\[N\\]\\` and\n\\`d_default_value\\` is a scalar.\n\n\nd_values\\[j\\] = grad_values\\[reverse_index_map\\[j\\]\\]\nd_default_value = sum_{k : 0 .. N_full - 1} (\ngrad_values\\[k\\] \\* 1{k not in reverse_index_map})\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n### Constants\n\n|--------|----------------------------------------------------------------------------------------|---------------------------------------------------------|\n| String | [OP_NAME](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseFillEmptyRowsGrad#OP_NAME) | The name of this op, as known by TensorFlow core engine |\n\n### Public Methods\n\n|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| static \\\u003cT extends [TType](/jvm/api_docs/java/org/tensorflow/types/family/TType)\\\u003e [SparseFillEmptyRowsGrad](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseFillEmptyRowsGrad)\\\u003cT\\\u003e | [create](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseFillEmptyRowsGrad#create(org.tensorflow.op.Scope, org.tensorflow.Operand\u003corg.tensorflow.types.TInt64\u003e, org.tensorflow.Operand\u003cT\u003e))([Scope](/jvm/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e reverseIndexMap, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003cT\\\u003e gradValues) Factory method to create a class wrapping a new SparseFillEmptyRowsGrad operation. |\n| [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003cT\\\u003e | [dDefaultValue](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseFillEmptyRowsGrad#dDefaultValue())() 0-D. |\n| [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003cT\\\u003e | [dValues](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseFillEmptyRowsGrad#dValues())() 1-D. |\n\n### Inherited Methods\n\nFrom class [org.tensorflow.op.RawOp](/jvm/api_docs/java/org/tensorflow/op/RawOp) \n\n|----------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| final boolean | [equals](/jvm/api_docs/java/org/tensorflow/op/RawOp#equals(java.lang.Object))(Object obj) |\n| final int | [hashCode](/jvm/api_docs/java/org/tensorflow/op/RawOp#hashCode())() |\n| [Operation](/jvm/api_docs/java/org/tensorflow/Operation) | [op](/jvm/api_docs/java/org/tensorflow/op/RawOp#op())() Return this unit of computation as a single [Operation](/jvm/api_docs/java/org/tensorflow/Operation). |\n| final String | [toString](/jvm/api_docs/java/org/tensorflow/op/RawOp#toString())() |\n\nFrom class java.lang.Object \n\n|------------------|---------------------------|\n| boolean | equals(Object arg0) |\n| final Class\\\u003c?\\\u003e | getClass() |\n| int | hashCode() |\n| final void | notify() |\n| final void | notifyAll() |\n| String | toString() |\n| final void | wait(long arg0, int arg1) |\n| final void | wait(long arg0) |\n| final void | wait() |\n\nFrom interface [org.tensorflow.op.Op](/jvm/api_docs/java/org/tensorflow/op/Op) \n\n|-----------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| abstract [ExecutionEnvironment](/jvm/api_docs/java/org/tensorflow/ExecutionEnvironment) | [env](/jvm/api_docs/java/org/tensorflow/op/Op#env())() Return the execution environment this op was created in. |\n| abstract [Operation](/jvm/api_docs/java/org/tensorflow/Operation) | [op](/jvm/api_docs/java/org/tensorflow/op/Op#op())() Return this unit of computation as a single [Operation](/jvm/api_docs/java/org/tensorflow/Operation). |\n\nConstants\n---------\n\n#### public static final String\n**OP_NAME**\n\nThe name of this op, as known by TensorFlow core engine \nConstant Value: \"SparseFillEmptyRowsGrad\"\n\nPublic Methods\n--------------\n\n#### public static [SparseFillEmptyRowsGrad](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseFillEmptyRowsGrad)\\\u003cT\\\u003e\n**create**\n([Scope](/jvm/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e reverseIndexMap, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003cT\\\u003e gradValues)\n\nFactory method to create a class wrapping a new SparseFillEmptyRowsGrad operation. \n\n##### Parameters\n\n| scope | current scope |\n| reverseIndexMap | 1-D. The reverse index map from SparseFillEmptyRows. |\n| gradValues | 1-D. The gradients from backprop. |\n|-----------------|------------------------------------------------------|\n\n##### Returns\n\n- a new instance of SparseFillEmptyRowsGrad \n\n#### public [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003cT\\\u003e\n**dDefaultValue**\n()\n\n0-D. The backprop into default_value. \n\n#### public [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003cT\\\u003e\n**dValues**\n()\n\n1-D. The backprop into values."]]
