public static final class Word2VecV3.Word2VecParametersV3 extends water.api.ModelParametersSchema<Word2VecModel.Word2VecParameters,Word2VecV3.Word2VecParametersV3>
| Modifier and Type | Field and Description |
|---|---|
int |
epochs |
float |
initLearningRate |
int |
minWordFreq |
int |
negSampleCnt |
Word2Vec.NormModel |
normModel |
static java.lang.String[] |
own_fields |
float |
sentSampleRate |
int |
vecSize |
int |
windowSize |
Word2Vec.WordModel |
wordModel |
| Constructor and Description |
|---|
Word2VecV3.Word2VecParametersV3() |
append_field_arrays, fields, fillFromImpl, fillImpl, writeParametersJSONcreateAndFillImpl, createImpl, fillFromParms, fillFromParms, get__meta, getExperimentalVersion, getHighestSupportedVersion, getImplClass, getImplClass, getLatestVersion, getSchemaVersion, markdown, markdown, markdown, newInstance, newInstance, registerAllSchemasIfNecessary, schema, schema, schemaClass, schemas, setFieldpublic static java.lang.String[] own_fields
@API(help="Set size of word vectors",
required=true)
public int vecSize
@API(help="Set max skip length between words",
required=true)
public int windowSize
@API(help="Set threshold for occurrence of words. Those that appear with higher frequency in the training data\n\t\twill be randomly down-sampled; useful range is (0, 1e-5)",
required=true)
public float sentSampleRate
@API(help="Use Hierarchical Softmax or Negative Sampling",
values={"HSM","NegSampling"},
required=true)
public Word2Vec.NormModel normModel
@API(help="Number of negative examples, common values are 3 - 10 (0 = not used)",
required=true)
public int negSampleCnt
@API(help="Number of training iterations to run",
required=true)
public int epochs
@API(help="This will discard words that appear less thantimes", required=true) public int minWordFreq
@API(help="Set the starting learning rate",
required=true)
public float initLearningRate
@API(help="Use the continuous bag of words model or the Skip-Gram model",
values={"CBOW","SkipGram"},
required=true)
public Word2Vec.WordModel wordModel