Class

com.johnsnowlabs.ml.tensorflow

TensorflowAlbertClassification

Related Doc: package tensorflow

Permalink

class TensorflowAlbertClassification extends Serializable with TensorflowForClassification

Linear Supertypes
TensorflowForClassification, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. TensorflowAlbertClassification
  2. TensorflowForClassification
  3. Serializable
  4. Serializable
  5. AnyRef
  6. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new TensorflowAlbertClassification(tensorflowWrapper: TensorflowWrapper, spp: SentencePieceWrapper, configProtoBytes: Option[Array[Byte]] = None, tags: Map[String, Int], signatures: Option[Map[String, String]] = None)

    Permalink

    tensorflowWrapper

    ALBERT Model wrapper with TensorFlow Wrapper

    spp

    ALBERT SentencePiece model with SentencePieceWrapper

    configProtoBytes

    Configuration for TensorFlow session

    tags

    labels which model was trained with in order

    signatures

    TF v2 signatures in Spark NLP

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  4. val _tfAlbertSignatures: Map[String, String]

    Permalink

  5. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  6. def calculateSoftmax(scores: Array[Float]): Array[Float]

    Permalink
    Definition Classes
    TensorflowForClassification

  7. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  8. def encode(sentences: Seq[(WordpieceTokenizedSentence, Int)], maxSequenceLength: Int): Seq[Array[Int]]

    Permalink

    Encode the input sequence to indexes IDs adding padding where necessary

    Encode the input sequence to indexes IDs adding padding where necessary

    Definition Classes
    TensorflowForClassification

  9. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  10. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  11. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  12. def findIndexedToken(tokenizedSentences: Seq[TokenizedSentence], sentence: (WordpieceTokenizedSentence, Int), tokenPiece: TokenPiece): Option[IndexedToken]

    Permalink
    Definition Classes
    TensorflowAlbertClassification → TensorflowForClassification

  13. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any

  14. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  15. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  16. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  17. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  18. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  19. def predict(tokenizedSentences: Seq[TokenizedSentence], batchSize: Int, maxSentenceLength: Int, caseSensitive: Boolean, tags: Map[String, Int]): Seq[Annotation]

    Permalink
    Definition Classes
    TensorflowForClassification

  20. val sentenceEndTokenId: Int

    Permalink
    Attributes
    protected
    Definition Classes
    TensorflowAlbertClassification → TensorflowForClassification

  21. val sentencePadTokenId: Int

    Permalink
    Attributes
    protected
    Definition Classes
    TensorflowAlbertClassification → TensorflowForClassification

  22. val sentenceStartTokenId: Int

    Permalink
    Attributes
    protected
    Definition Classes
    TensorflowAlbertClassification → TensorflowForClassification

  23. val spp: SentencePieceWrapper

    Permalink

    ALBERT SentencePiece model with SentencePieceWrapper

  24. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef

  25. def tag(batch: Seq[Array[Int]]): Seq[Array[Array[Float]]]

    Permalink
    Definition Classes
    TensorflowAlbertClassification → TensorflowForClassification

  26. val tensorflowWrapper: TensorflowWrapper

    Permalink

    ALBERT Model wrapper with TensorFlow Wrapper

  27. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  28. def tokenizeWithAlignment(sentences: Seq[TokenizedSentence], maxSeqLength: Int, caseSensitive: Boolean): Seq[WordpieceTokenizedSentence]

    Permalink
    Definition Classes
    TensorflowAlbertClassification → TensorflowForClassification

  29. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  30. final def wait(arg0: Long, arg1: Int): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  31. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  32. def wordAndSpanLevelAlignmentWithTokenizer(tokenLogits: Array[Array[Float]], tokenizedSentences: Seq[TokenizedSentence], sentence: (WordpieceTokenizedSentence, Int), tags: Map[String, Int]): Seq[Annotation]

    Permalink

    Word-level and span-level alignment with Tokenizer https://github.com/google-research/bert#tokenization

    Word-level and span-level alignment with Tokenizer https://github.com/google-research/bert#tokenization

    ### Input orig_tokens = ["John", "Johanson", "'s", "house"] labels = ["NNP", "NNP", "POS", "NN"]

    # bert_tokens == ["[CLS]", "john", "johan", "##son", "'", "s", "house", "[SEP]"] # orig_to_tok_map == [1, 2, 4, 6]

    Definition Classes
    TensorflowForClassification

Inherited from TensorflowForClassification

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped