SparseReshape
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Membentuk ulang SparseTensor untuk mewakili nilai dalam bentuk padat baru.
Operasi ini memiliki semantik yang sama dengan pembentukan ulang pada tensor padat yang diwakili. `Input_indices` dihitung ulang berdasarkan `new_shape` yang diminta.
Jika salah satu komponen `bentuk_baru` memiliki nilai khusus -1, ukuran dimensi tersebut dihitung sehingga ukuran padat total tetap konstan. Maksimal satu komponen `new_shape` bisa bernilai -1. Jumlah elemen padat yang ditunjukkan oleh `bentuk_baru` harus sama dengan jumlah elemen padat yang awalnya ditunjukkan oleh `bentuk_input`.
Pembentukan ulang tidak memengaruhi urutan nilai di SparseTensor.
Jika tensor input memiliki nilai rank `R_in` dan `N` yang tidak kosong, dan `new_shape` memiliki panjang `R_out`, maka `input_indices` memiliki bentuk `[N, R_in]`, `input_shape` memiliki panjang `R_in` , `output_indices` berbentuk `[N, R_out]`, dan `output_shape` memiliki panjang `R_out`.
Konstanta
| Rangkaian | OP_NAME | Nama operasi ini dikenal dengan mesin inti TensorFlow |
Metode Warisan
Dari kelas java.lang.Object | boolean | sama dengan (Objek arg0) |
| Kelas terakhir<?> | dapatkan Kelas () |
| ke dalam | Kode hash () |
| kekosongan terakhir | memberitahu () |
| kekosongan terakhir | beri tahuSemua () |
| Rangkaian | keString () |
| kekosongan terakhir | tunggu (arg0 panjang, int arg1) |
| kekosongan terakhir | tunggu (argumen panjang0) |
| kekosongan terakhir | Tunggu () |
Konstanta
String akhir statis publik OP_NAME
Nama operasi ini dikenal dengan mesin inti TensorFlow
Nilai Konstan: "SparseReshape"
Metode Publik
Metode pabrik untuk membuat kelas yang membungkus operasi SparseReshape baru.
Parameter
| cakupan | ruang lingkup saat ini |
|---|
| masukanIndeks | 2-D. Matriks `N x R_in` dengan indeks nilai tidak kosong di SparseTensor. |
|---|
| bentuk masukan | 1-D. Vektor `R_in` dengan input bentuk padat SparseTensor. |
|---|
| Bentuk baru | 1-D. Vektor `R_out` dengan bentuk padat baru yang diminta. |
|---|
Kembali
- contoh baru dari SparseReshape
Keluaran publik < TInt64 > Indeks keluaran ()
2-D. Matriks `N x R_out` dengan indeks nilai tidak kosong yang diperbarui di output SparseTensor.
Keluaran publik < TInt64 > bentuk keluaran ()
1-D. Vektor `R_out` dengan bentuk padat penuh dari keluaran SparseTensor. Ini sama dengan `bentuk_baru` tetapi dengan -1 dimensi apa pun yang terisi.
Kecuali dinyatakan lain, konten di halaman ini dilisensikan berdasarkan Lisensi Creative Commons Attribution 4.0, sedangkan contoh kode dilisensikan berdasarkan Lisensi Apache 2.0. Untuk mengetahui informasi selengkapnya, lihat Kebijakan Situs Google Developers. Java adalah merek dagang terdaftar dari Oracle dan/atau afiliasinya.
Terakhir diperbarui pada 2025-07-26 UTC.
[null,null,["Terakhir diperbarui pada 2025-07-26 UTC."],[],[],null,["# SparseReshape\n\npublic final class **SparseReshape** \nReshapes a SparseTensor to represent values in a new dense shape.\n\n\nThis operation has the same semantics as reshape on the represented dense\ntensor. The \\`input_indices\\` are recomputed based on the requested \\`new_shape\\`.\n\n\nIf one component of \\`new_shape\\` is the special value -1, the size of that\ndimension is computed so that the total dense size remains constant. At\nmost one component of \\`new_shape\\` can be -1. The number of dense elements\nimplied by \\`new_shape\\` must be the same as the number of dense elements\noriginally implied by \\`input_shape\\`.\n\n\nReshaping does not affect the order of values in the SparseTensor.\n\n\nIf the input tensor has rank \\`R_in\\` and \\`N\\` non-empty values, and \\`new_shape\\`\nhas length \\`R_out\\`, then \\`input_indices\\` has shape \\`\\[N, R_in\\]\\`,\n\\`input_shape\\` has length \\`R_in\\`, \\`output_indices\\` has shape \\`\\[N, R_out\\]\\`, and\n\\`output_shape\\` has length \\`R_out\\`.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n### Constants\n\n|--------|------------------------------------------------------------------------------|---------------------------------------------------------|\n| String | [OP_NAME](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseReshape#OP_NAME) | The name of this op, as known by TensorFlow core engine |\n\n### Public Methods\n\n|----------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| static [SparseReshape](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseReshape) | [create](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseReshape#create(org.tensorflow.op.Scope, org.tensorflow.Operand\u003corg.tensorflow.types.TInt64\u003e, org.tensorflow.Operand\u003corg.tensorflow.types.TInt64\u003e, org.tensorflow.Operand\u003corg.tensorflow.types.TInt64\u003e))([Scope](/jvm/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e inputIndices, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e inputShape, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e newShape) Factory method to create a class wrapping a new SparseReshape operation. |\n| [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e | [outputIndices](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseReshape#outputIndices())() 2-D. |\n| [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e | [outputShape](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseReshape#outputShape())() 1-D. |\n\n### Inherited Methods\n\nFrom class [org.tensorflow.op.RawOp](/jvm/api_docs/java/org/tensorflow/op/RawOp) \n\n|----------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| final boolean | [equals](/jvm/api_docs/java/org/tensorflow/op/RawOp#equals(java.lang.Object))(Object obj) |\n| final int | [hashCode](/jvm/api_docs/java/org/tensorflow/op/RawOp#hashCode())() |\n| [Operation](/jvm/api_docs/java/org/tensorflow/Operation) | [op](/jvm/api_docs/java/org/tensorflow/op/RawOp#op())() Return this unit of computation as a single [Operation](/jvm/api_docs/java/org/tensorflow/Operation). |\n| final String | [toString](/jvm/api_docs/java/org/tensorflow/op/RawOp#toString())() |\n\nFrom class java.lang.Object \n\n|------------------|---------------------------|\n| boolean | equals(Object arg0) |\n| final Class\\\u003c?\\\u003e | getClass() |\n| int | hashCode() |\n| final void | notify() |\n| final void | notifyAll() |\n| String | toString() |\n| final void | wait(long arg0, int arg1) |\n| final void | wait(long arg0) |\n| final void | wait() |\n\nFrom interface [org.tensorflow.op.Op](/jvm/api_docs/java/org/tensorflow/op/Op) \n\n|-----------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| abstract [ExecutionEnvironment](/jvm/api_docs/java/org/tensorflow/ExecutionEnvironment) | [env](/jvm/api_docs/java/org/tensorflow/op/Op#env())() Return the execution environment this op was created in. |\n| abstract [Operation](/jvm/api_docs/java/org/tensorflow/Operation) | [op](/jvm/api_docs/java/org/tensorflow/op/Op#op())() Return this unit of computation as a single [Operation](/jvm/api_docs/java/org/tensorflow/Operation). |\n\nConstants\n---------\n\n#### public static final String\n**OP_NAME**\n\nThe name of this op, as known by TensorFlow core engine \nConstant Value: \"SparseReshape\"\n\nPublic Methods\n--------------\n\n#### public static [SparseReshape](/jvm/api_docs/java/org/tensorflow/op/sparse/SparseReshape)\n**create**\n([Scope](/jvm/api_docs/java/org/tensorflow/op/Scope) scope, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e inputIndices, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e inputShape, [Operand](/jvm/api_docs/java/org/tensorflow/Operand)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e newShape)\n\nFactory method to create a class wrapping a new SparseReshape operation. \n\n##### Parameters\n\n| scope | current scope |\n| inputIndices | 2-D. \\`N x R_in\\` matrix with the indices of non-empty values in a SparseTensor. |\n| inputShape | 1-D. \\`R_in\\` vector with the input SparseTensor's dense shape. |\n| newShape | 1-D. \\`R_out\\` vector with the requested new dense shape. |\n|--------------|----------------------------------------------------------------------------------|\n\n##### Returns\n\n- a new instance of SparseReshape \n\n#### public [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e\n**outputIndices**\n()\n\n2-D. \\`N x R_out\\` matrix with the updated indices of non-empty\nvalues in the output SparseTensor. \n\n#### public [Output](/jvm/api_docs/java/org/tensorflow/Output)\\\u003c[TInt64](/jvm/api_docs/java/org/tensorflow/types/TInt64)\\\u003e\n**outputShape**\n()\n\n1-D. \\`R_out\\` vector with the full dense shape of the output\nSparseTensor. This is the same as \\`new_shape\\` but with any -1 dimensions\nfilled in."]]
