TensorflowDistilBertClassification

Instance Constructors

new TensorflowDistilBertClassification(tensorflowWrapper: TensorflowWrapper, sentenceStartTokenId: Int, sentenceEndTokenId: Int, configProtoBytes: Option[Array[Byte]] = None, tags: Map[String, Int], signatures: Option[Map[String, String]] = None, vocabulary: Map[String, Int])

tensorflowWrapper
Bert Model wrapper with TensorFlow Wrapper
sentenceStartTokenId
Id of sentence start Token
sentenceEndTokenId
Id of sentence end Token.
configProtoBytes
Configuration for TensorFlow session
tags
labels which model was trained with in order
signatures
TF v2 signatures in Spark NLP

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
val _tfDistilBertSignatures: Map[String, String]
final def asInstanceOf[T0]: T0

Definition Classes
Any
def calculateSigmoid(scores: Array[Float]): Array[Float]

Calcuate sigmoid from returned logits
Calcuate sigmoid from returned logits
scores
logits output from output layer

Definition Classes
TensorflowForClassification
def calculateSoftmax(scores: Array[Float]): Array[Float]

Calcuate softmax from retruned logits
Calcuate softmax from retruned logits
scores
logits output from output layer

Definition Classes
TensorflowForClassification
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def constructAnnotationForSequenceClassifier(sentence: Sentence, label: String, meta: Array[(String, String)]): Annotation

Definition Classes
TensorflowForClassification
def constructMetaForSequenceClassifier(tags: Map[String, Int], scores: Array[Float]): Array[(String, String)]

Definition Classes
TensorflowForClassification
def encode(sentences: Seq[(WordpieceTokenizedSentence, Int)], maxSequenceLength: Int): Seq[Array[Int]]

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
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def findIndexedToken(tokenizedSentences: Seq[TokenizedSentence], sentence: (WordpieceTokenizedSentence, Int), tokenPiece: TokenPiece): Option[IndexedToken]

Definition Classes
TensorflowDistilBertClassification → TensorflowForClassification
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

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

Definition Classes
TensorflowForClassification
def predictSequence(tokenizedSentences: Seq[TokenizedSentence], sentences: Seq[Sentence], batchSize: Int, maxSentenceLength: Int, caseSensitive: Boolean, coalesceSentences: Boolean = false, tags: Map[String, Int], activation: String = ActivationFunction.softmax): Seq[Annotation]

Definition Classes
TensorflowForClassification
def scoresToLabelForSequenceClassifier(tags: Map[String, Int], scores: Array[Float]): String

Definition Classes
TensorflowForClassification
val sentenceEndTokenId: Int

Id of sentence end Token.
Id of sentence end Token.

Definition Classes
TensorflowDistilBertClassification → TensorflowForClassification
val sentencePadTokenId: Int

Attributes
protected
Definition Classes
TensorflowDistilBertClassification → TensorflowForClassification
val sentenceStartTokenId: Int

Id of sentence start Token
Id of sentence start Token

Definition Classes
TensorflowDistilBertClassification → TensorflowForClassification
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def tag(batch: Seq[Array[Int]]): Seq[Array[Array[Float]]]

Definition Classes
TensorflowDistilBertClassification → TensorflowForClassification
def tagSequence(batch: Seq[Array[Int]], activation: String): Array[Array[Float]]

Definition Classes
TensorflowDistilBertClassification → TensorflowForClassification
val tensorflowWrapper: TensorflowWrapper

Bert Model wrapper with TensorFlow Wrapper
def toString(): String

Definition Classes
AnyRef → Any
def tokenizeWithAlignment(sentences: Seq[TokenizedSentence], maxSeqLength: Int, caseSensitive: Boolean): Seq[WordpieceTokenizedSentence]

Definition Classes
TensorflowDistilBertClassification → TensorflowForClassification
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
def wordAndSpanLevelAlignmentWithTokenizer(tokenLogits: Array[Array[Float]], tokenizedSentences: Seq[TokenizedSentence], sentence: (WordpieceTokenizedSentence, Int), tags: Map[String, Int]): Seq[Annotation]

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

Related Doc: package tensorflow

class TensorflowDistilBertClassification extends Serializable with TensorflowForClassification

Instance Constructors

new TensorflowDistilBertClassification(tensorflowWrapper: TensorflowWrapper, sentenceStartTokenId: Int, sentenceEndTokenId: Int, configProtoBytes: Option[Array[Byte]] = None, tags: Map[String, Int], signatures: Option[Map[String, String]] = None, vocabulary: Map[String, Int])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

val _tfDistilBertSignatures: Map[String, String]

final def asInstanceOf[T0]: T0

def calculateSigmoid(scores: Array[Float]): Array[Float]

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

def clone(): AnyRef

def constructAnnotationForSequenceClassifier(sentence: Sentence, label: String, meta: Array[(String, String)]): Annotation

def constructMetaForSequenceClassifier(tags: Map[String, Int], scores: Array[Float]): Array[(String, String)]

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

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

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

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

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

def predictSequence(tokenizedSentences: Seq[TokenizedSentence], sentences: Seq[Sentence], batchSize: Int, maxSentenceLength: Int, caseSensitive: Boolean, coalesceSentences: Boolean = false, tags: Map[String, Int], activation: String = ActivationFunction.softmax): Seq[Annotation]

def scoresToLabelForSequenceClassifier(tags: Map[String, Int], scores: Array[Float]): String

val sentenceEndTokenId: Int

val sentencePadTokenId: Int

val sentenceStartTokenId: Int

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

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

def tagSequence(batch: Seq[Array[Int]], activation: String): Array[Array[Float]]

val tensorflowWrapper: TensorflowWrapper

def toString(): String

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

final def wait(): Unit

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

final def wait(arg0: Long): Unit

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

Inherited from TensorflowForClassification

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped