Class Reuters
Dataset of 11,228 newswires from Reuters, labeled over 46 topics. As with the IMDB dataset, each wire is encoded as a sequence of word indexes (same conventions).
Implements
System.IDisposable
Inherited Members
System.Object.Equals(System.Object)
System.Object.Equals(System.Object, System.Object)
System.Object.GetHashCode()
System.Object.GetType()
System.Object.MemberwiseClone()
System.Object.ReferenceEquals(System.Object, System.Object)
System.Object.ToString()
Namespace: Keras.Datasets
Assembly: Keras.dll
Syntax
public class Reuters : Base, IDisposable
Methods
| Improve this Doc View SourceLoadData(String, Nullable<Int32>, Int32, Nullable<Int32>, Single, Int32, Int32, Int32, Int32)
Loads the data.
Declaration
public static ((NDarray, NDarray), (NDarray, NDarray))LoadData(string path = "reuters.npz", int? num_words = default(int? ), int skip_top = 0, int? maxlen = default(int? ), float test_split = 0.2F, int seed = 113, int start_char = 1, int oov_char = 2, int index_from = 3)
Parameters
Type | Name | Description |
---|---|---|
System.String | path | The path. to load text |
System.Nullable<System.Int32> | num_words | The number words. |
System.Int32 | skip_top | Skip top number of records. |
System.Nullable<System.Int32> | maxlen | The max length. |
System.Single | test_split | The test split. |
System.Int32 | seed | The seed. |
System.Int32 | start_char | The start character. |
System.Int32 | oov_char | The oov character. |
System.Int32 | index_from | The index from. |
Returns
Type | Description |
---|---|
System.ValueTuple<System.ValueTuple<Numpy.NDarray, Numpy.NDarray>, System.ValueTuple<Numpy.NDarray, Numpy.NDarray>> |
Implements
System.IDisposable