Aprenda o que há de mais recente em aprendizado de máquina, IA generativa e muito mais no WiML Symposium 2023
Registre-se
QuantizedRelu6
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
Calcula o Linear Retificado Quantizado 6: `min (max (recursos, 0), 6)`
Constantes
| Fragmento | OP_NAME | O nome desta operação, conforme conhecido pelo motor principal TensorFlow |
Métodos herdados
Da classe java.lang.Object | boleano | equals (arg0 Object) |
| aula final <?> | getClass () |
| int | hashCode () |
| vazio final | notificar () |
| vazio final | notifyAll () |
| Fragmento | toString () |
| vazio final | wait (longa arg0, int arg1) |
| vazio final | wait (arg0 de comprimento) |
| vazio final | wait () |
Constantes
nome_op final String public static
O nome desta operação, conforme conhecido pelo motor principal TensorFlow
Valor constante: "QuantizedRelu6"
Métodos Públicos
pública Output <U> ativações ()
Tem o mesmo formato de saída que "recursos".
Método de fábrica para criar uma classe envolvendo uma nova operação QuantizedRelu6.
Parâmetros
| alcance | escopo atual |
|---|
| minFeatures | O valor flutuante que o menor valor quantizado representa. |
|---|
| maxFeatures | O valor flutuante que o maior valor quantizado representa. |
|---|
Devoluções
- uma nova instância de QuantizedRelu6
pública Output < TFloat32 > maxActivations ()
O valor flutuante que o maior valor quantizado representa.
pública Output < TFloat32 > minActivations ()
O valor flutuante que o menor valor quantizado representa.
Exceto em caso de indicação contrária, o conteúdo desta página é licenciado de acordo com a Licença de atribuição 4.0 do Creative Commons, e as amostras de código são licenciadas de acordo com a Licença Apache 2.0. Para mais detalhes, consulte as políticas do site do Google Developers. Java é uma marca registrada da Oracle e/ou afiliadas.
Última atualização 2021-11-29 UTC.
[null,null,["Última atualização 2021-11-29 UTC."],[],[],null,["# QuantizedRelu6\n\npublic final class **QuantizedRelu6** \nComputes Quantized Rectified Linear 6: \\`min(max(features, 0), 6)\\` \n\n### Constants\n\n|--------|---------------------------------------------------------------------------|---------------------------------------------------------|\n| String | [OP_NAME](/jvm/api_docs/java/org/tensorflow/op/nn/QuantizedRelu6#OP_NAME) | The name of this op, as known by TensorFlow core engine |\n\n### Public Methods\n\n|------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003cU\\\u003e | [activations](/jvm/api_docs/java/org/tensorflow/op/nn/QuantizedRelu6#activations())() Has the same output shape as \"features\". |\n| static \\\u003cU extends [TType](/jvm/api_docs/java/org/tensorflow/types/family/TType)\\\u003e [QuantizedRelu6](/jvm/api_docs/java/org/tensorflow/op/nn/QuantizedRelu6)\\\u003cU\\\u003e | [create](/jvm/api_docs/java/org/tensorflow/op/nn/QuantizedRelu6#create(org.tensorflow.op.Scope, org.tensorflow.Operand\u003c? extends org.tensorflow.types.family.TType\u003e, org.tensorflow.Operand\u003corg.tensorflow.types.TFloat32\u003e, org.tensorflow.Operand\u003corg.tensorflow.types.TFloat32\u003e, java.lang.Class\u003cU\u003e))([Scope](/jvm/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c? extends [TType](/jvm/api_docs/java/org/tensorflow/types/family/TType)\\\u003e features, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e minFeatures, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e maxFeatures, Class\\\u003cU\\\u003e outType) Factory method to create a class wrapping a new QuantizedRelu6 operation. |\n| [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e | [maxActivations](/jvm/api_docs/java/org/tensorflow/op/nn/QuantizedRelu6#maxActivations())() The float value that the highest quantized value represents. |\n| [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e | [minActivations](/jvm/api_docs/java/org/tensorflow/op/nn/QuantizedRelu6#minActivations())() The float value that the lowest quantized value represents. |\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: \"QuantizedRelu6\"\n\nPublic Methods\n--------------\n\n#### public [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003cU\\\u003e\n**activations**\n()\n\nHas the same output shape as \"features\". \n\n#### public static [QuantizedRelu6](/jvm/api_docs/java/org/tensorflow/op/nn/QuantizedRelu6)\\\u003cU\\\u003e\n**create**\n([Scope](/jvm/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c? extends [TType](/jvm/api_docs/java/org/tensorflow/types/family/TType)\\\u003e features, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e minFeatures, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e maxFeatures, Class\\\u003cU\\\u003e outType)\n\nFactory method to create a class wrapping a new QuantizedRelu6 operation. \n\n##### Parameters\n\n| scope | current scope |\n| minFeatures | The float value that the lowest quantized value represents. |\n| maxFeatures | The float value that the highest quantized value represents. |\n|-------------|--------------------------------------------------------------|\n\n##### Returns\n\n- a new instance of QuantizedRelu6 \n\n#### public [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e\n**maxActivations**\n()\n\nThe float value that the highest quantized value represents. \n\n#### public [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TFloat32](/jvm/api_docs/java/org/tensorflow/types/TFloat32)\\\u003e\n**minActivations**\n()\n\nThe float value that the lowest quantized value represents."]]
