org.tensorflow
Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
Definisce le classi per creare, salvare, caricare ed eseguire modelli TensorFlow.
ATTENZIONE : l'API è attualmente sperimentale e non è coperta dalle garanzie di stabilità dell'API TensorFlow. Vedere README.md per le istruzioni di installazione.
L'esempio LabelImage dimostra l'uso di questa API per classificare le immagini utilizzando una rete neurale convoluzionale con architettura Inception preaddestrata. Dimostra:
- Costruzione del grafico: utilizzo della classe OperationBuilder per costruire un grafico per decodificare, ridimensionare e normalizzare un'immagine JPEG.
- Caricamento del modello: utilizzo di Graph.importGraphDef() per caricare un modello Inception preaddestrato.
- Esecuzione del grafico: utilizzo di una sessione per eseguire i grafici e trovare l'etichetta migliore per un'immagine.
Interfacce
Classi
Enumerazioni
Eccezioni
| TensorFlowException | Eccezione non controllata generata durante l'esecuzione di TensorFlow Graphs. |
Salvo quando diversamente specificato, i contenuti di questa pagina sono concessi in base alla licenza Creative Commons Attribution 4.0, mentre gli esempi di codice sono concessi in base alla licenza Apache 2.0. Per ulteriori dettagli, consulta le norme del sito di Google Developers. Java è un marchio registrato di Oracle e/o delle sue consociate.
Ultimo aggiornamento 2025-07-26 UTC.
[null,null,["Ultimo aggiornamento 2025-07-26 UTC."],[],[],null,["# org.tensorflow\n\nDefines classes to build, save, load and execute TensorFlow models.\n\n**WARNING** : The API is currently experimental and is not covered by TensorFlow [API stability guarantees](https://www.tensorflow.org/guide/version_compat). See [README.md](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/java/README.md)\nfor installation instructions.\n\nThe [LabelImage](https://www.tensorflow.org/code/tensorflow/java/src/main/java/org/tensorflow/examples/LabelImage.java)\nexample demonstrates use of this API to classify images using a pre-trained [Inception](http://arxiv.org/abs/1512.00567) architecture convolutional neural network.\nIt demonstrates:\n\n- Graph construction: using the OperationBuilder class to construct a graph to decode, resize and normalize a JPEG image.\n- Model loading: Using Graph.importGraphDef() to load a pre-trained Inception model.\n- Graph execution: Using a Session to execute the graphs and find the best label for an image.\n\n### Interfaces\n\n|--------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------|\n| [ExecutionEnvironment](/api_docs/java/reference/org/tensorflow/ExecutionEnvironment) | Defines an environment for creating and executing TensorFlow [Operation](/api_docs/java/reference/org/tensorflow/Operation)s. |\n| [Graph.WhileSubgraphBuilder](/api_docs/java/reference/org/tensorflow/Graph.WhileSubgraphBuilder) | Used to instantiate an abstract class which overrides the buildSubgraph method to build a conditional or body subgraph for a while loop. |\n| [Operand](/api_docs/java/reference/org/tensorflow/Operand)\\\u003cT\\\u003e | Interface implemented by operands of a TensorFlow operation. |\n| [Operation](/api_docs/java/reference/org/tensorflow/Operation) | Performs computation on Tensors. |\n| [OperationBuilder](/api_docs/java/reference/org/tensorflow/OperationBuilder) | A builder for [Operation](/api_docs/java/reference/org/tensorflow/Operation)s. |\n\n### Classes\n\n|--------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [EagerSession](/api_docs/java/reference/org/tensorflow/EagerSession) | An environment for executing TensorFlow operations eagerly. |\n| [EagerSession.Options](/api_docs/java/reference/org/tensorflow/EagerSession.Options) | |\n| [Graph](/api_docs/java/reference/org/tensorflow/Graph) | A data flow graph representing a TensorFlow computation. |\n| [GraphOperation](/api_docs/java/reference/org/tensorflow/GraphOperation) | Implementation for an [Operation](/api_docs/java/reference/org/tensorflow/Operation) added as a node to a [Graph](/api_docs/java/reference/org/tensorflow/Graph). |\n| [GraphOperationBuilder](/api_docs/java/reference/org/tensorflow/GraphOperationBuilder) | An [OperationBuilder](/api_docs/java/reference/org/tensorflow/OperationBuilder) for adding [GraphOperation](/api_docs/java/reference/org/tensorflow/GraphOperation)s to a [Graph](/api_docs/java/reference/org/tensorflow/Graph). |\n| [Output](/api_docs/java/reference/org/tensorflow/Output)\\\u003cT\\\u003e | A symbolic handle to a tensor produced by an [Operation](/api_docs/java/reference/org/tensorflow/Operation). |\n| [SavedModelBundle](/api_docs/java/reference/org/tensorflow/SavedModelBundle) | SavedModelBundle represents a model loaded from storage. |\n| [SavedModelBundle.Loader](/api_docs/java/reference/org/tensorflow/SavedModelBundle.Loader) | Options for loading a SavedModel. |\n| [Server](/api_docs/java/reference/org/tensorflow/Server) | An in-process TensorFlow server, for use in distributed training. |\n| [Session](/api_docs/java/reference/org/tensorflow/Session) | Driver for [Graph](/api_docs/java/reference/org/tensorflow/Graph) execution. |\n| [Session.Run](/api_docs/java/reference/org/tensorflow/Session.Run) | Output tensors and metadata obtained when executing a session. |\n| [Session.Runner](/api_docs/java/reference/org/tensorflow/Session.Runner) | Run [Operation](/api_docs/java/reference/org/tensorflow/Operation)s and evaluate [Tensors](/api_docs/java/reference/org/tensorflow/Tensor). |\n| [Shape](/api_docs/java/reference/org/tensorflow/Shape) | The possibly partially known shape of a tensor produced by an operation. |\n| [Tensor](/api_docs/java/reference/org/tensorflow/Tensor)\\\u003cT\\\u003e | A statically typed multi-dimensional array whose elements are of a type described by T. |\n| [TensorFlow](/api_docs/java/reference/org/tensorflow/TensorFlow) | Static utility methods describing the TensorFlow runtime. |\n| [Tensors](/api_docs/java/reference/org/tensorflow/Tensors) | Type-safe factory methods for creating [Tensor](/api_docs/java/reference/org/tensorflow/Tensor) objects. |\n\n### Enums\n\n|----------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------|\n| [DataType](/api_docs/java/reference/org/tensorflow/DataType) | Represents the type of elements in a [Tensor](/api_docs/java/reference/org/tensorflow/Tensor) as an enum. |\n| [EagerSession.DevicePlacementPolicy](/api_docs/java/reference/org/tensorflow/EagerSession.DevicePlacementPolicy) | Controls how to act when we try to run an operation on a given device but some input tensors are not on that device. |\n| [EagerSession.ResourceCleanupStrategy](/api_docs/java/reference/org/tensorflow/EagerSession.ResourceCleanupStrategy) | Controls how TensorFlow resources are cleaned up when they are no longer needed. |\n\n### Exceptions\n\n|------------------------------------------------------------------------------------|--------------------------------------------------------------|\n| [TensorFlowException](/api_docs/java/reference/org/tensorflow/TensorFlowException) | Unchecked exception thrown when executing TensorFlow Graphs. |"]]
