Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
aliran tensor:: operasi:: SparseFillEmptyRows
#include <sparse_ops.h> Mengisi baris kosong di input 2-D SparseTensor dengan nilai default.
Ringkasan
Input SparseTensor direpresentasikan melalui tupel input ( indices , values , dense_shape ). Outputnya SparseTensor memiliki dense_shape yang sama tetapi dengan indeks output_indices dan nilai output_values .
Operasi ini menyisipkan satu entri untuk setiap baris yang tidak memiliki nilai apa pun. Indeks dibuat sebagai [row, 0, ..., 0] dan nilai yang dimasukkan adalah default_value .
Misalnya, sp_input memiliki bentuk [5, 6] dan nilai tidak kosong:
[0, 1]: a
[0, 3]: b
[2, 0]: c
[3, 1]: d
Baris 1 dan 4 kosong, sehingga keluarannya akan berbentuk [5, 6] dengan nilai:
[0, 1]: a
[0, 3]: b
[1, 0]: default_value
[2, 0]: c
[3, 1]: d
[4, 0]: default_value
Output SparseTensor akan berada dalam urutan baris-mayor dan akan memiliki bentuk yang sama dengan input.
Operasi ini juga mengembalikan vektor indikator berbentuk [dense_shape[0]] sedemikian rupa
empty_row_indicator[i] = True iff row i was an empty row.
Dan peta indeks terbalik berbentuk vektor [indices.shape[0]] yang digunakan selama backpropagation,
reverse_index_map[j] = out_j s.t. indices[j, :] == output_indices[out_j, :]
Argumen:
- ruang lingkup: Objek Lingkup
- indeks: 2-D. indeks tensor renggang.
- nilai: 1-D. nilai tensor renggang.
- padat_bentuk: 1-D. bentuk tensor renggang.
- nilai_default: 0-D. nilai default untuk dimasukkan ke lokasi
[row, 0, ..., 0] untuk baris yang hilang dari tensor renggang masukan. indeks keluaran: 2-D. indeks tensor renggang yang terisi.
Pengembalian:
-
Output keluaran_indeks - Nilai keluaran
Output : 1-D. nilai tensor renggang yang terisi. -
Output indikator_baris kosong: 1-D. apakah baris padat hilang di tensor renggang masukan. -
Output reverse_index_map: 1-D. peta dari indeks masukan ke indeks keluaran.
Atribut publik
Fungsi publik
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,["# tensorflow::ops::SparseFillEmptyRows Class Reference\n\ntensorflow::ops::SparseFillEmptyRows\n====================================\n\n`#include \u003csparse_ops.h\u003e`\n\nFills empty rows in the input 2-D `SparseTensor` with a default value.\n\nSummary\n-------\n\nThe input `SparseTensor` is represented via the tuple of inputs (`indices`, `values`, `dense_shape`). The output `SparseTensor` has the same `dense_shape` but with indices `output_indices` and values `output_values`.\n\nThis op inserts a single entry for every row that doesn't have any values. The index is created as `[row, 0, ..., 0]` and the inserted value is `default_value`.\n\nFor example, suppose `sp_input` has shape `[5, 6]` and non-empty values: \n\n```text\n[0, 1]: a\n[0, 3]: b\n[2, 0]: c\n[3, 1]: d\n```\n\n\u003cbr /\u003e\n\nRows 1 and 4 are empty, so the output will be of shape `[5, 6]` with values: \n\n```scdoc\n[0, 1]: a\n[0, 3]: b\n[1, 0]: default_value\n[2, 0]: c\n[3, 1]: d\n[4, 0]: default_value\n```\n\n\u003cbr /\u003e\n\nThe output `SparseTensor` will be in row-major order and will have the same shape as the input.\n\nThis op also returns an indicator vector shaped `[dense_shape[0]]` such that \n\n```transact-sql\nempty_row_indicator[i] = True iff row i was an empty row.\n```\n\n\u003cbr /\u003e\n\nAnd a reverse index map vector shaped `[indices.shape[0]]` that is used during backpropagation, \n\n```transact-sql\nreverse_index_map[j] = out_j s.t. indices[j, :] == output_indices[out_j, :]\n```\n\n\u003cbr /\u003e\n\nArguments:\n\n- scope: A [Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- indices: 2-D. the indices of the sparse tensor.\n- values: 1-D. the values of the sparse tensor.\n- dense_shape: 1-D. the shape of the sparse tensor.\n- default_value: 0-D. default value to insert into location `[row, 0, ..., 0]` for rows missing from the input sparse tensor. output indices: 2-D. the indices of the filled sparse tensor.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) output_indices\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) output_values: 1-D. the values of the filled sparse tensor.\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) empty_row_indicator: 1-D. whether the dense row was missing in the input sparse tensor.\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) reverse_index_map: 1-D. a map from the input indices to the output indices.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [SparseFillEmptyRows](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_1a879e72f00ec2907ae24319568619e724)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` indices, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` values, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` dense_shape, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` default_value)` ||\n\n| ### Public attributes ||\n|--------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [empty_row_indicator](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_1adb1b94f12679619031e52393d4dde736) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [operation](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_1a904fc23a9366dfb3edb6e9ce97f51176) | [Operation](/versions/r2.0/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output_indices](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_1a2e77eb808d738a81625bc66d14e269c2) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [output_values](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_1a050f6a03931adf4b1fe9fe0933537d4f) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [reverse_index_map](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_1af0519edc8137614dd36f96f10ed6e4ef) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\nPublic attributes\n-----------------\n\n### empty_row_indicator\n\n```scdoc\n::tensorflow::Output empty_row_indicator\n``` \n\n### operation\n\n```text\nOperation operation\n``` \n\n### output_indices\n\n```scdoc\n::tensorflow::Output output_indices\n``` \n\n### output_values\n\n```scdoc\n::tensorflow::Output output_values\n``` \n\n### reverse_index_map\n\n```scdoc\n::tensorflow::Output reverse_index_map\n``` \n\nPublic functions\n----------------\n\n### SparseFillEmptyRows\n\n```gdscript\n SparseFillEmptyRows(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input indices,\n ::tensorflow::Input values,\n ::tensorflow::Input dense_shape,\n ::tensorflow::Input default_value\n)\n```"]]
