Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
aliran tensor:: operasi:: SparseFillEmptyRowsGrad
#include <sparse_ops.h> Gradien SparseFillEmptyRows .
Ringkasan
Mengambil vektor reverse_index_map, berbentuk [N] , dan grad_values, berbentuk [N_full] , dengan N_full >= N dan menyalin data ke d_values atau d_default_value . Di sini d_values berbentuk [N] dan d_default_value adalah skalar.
d_values[j] = grad_values[reverse_index_map[j]] d_default_value = sum_{k : 0 .. N_full - 1} ( grad_values[k] * 1{k tidak ada di reverse_index_map})
Argumen:
- ruang lingkup: Objek Lingkup
- peta_indeks_terbalik: 1-D. Peta indeks terbalik dari SparseFillEmptyRows .
- nilai_graduasi: 1-D. Gradien dari backprop.
Pengembalian:
- Nilai
Output : 1-D. Backprop menjadi nilai. -
Output nilai_default: 0-D. Backprop menjadi default_value.
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 2025-07-25 UTC.
[null,null,["Terakhir diperbarui pada 2025-07-25 UTC."],[],[],null,["# tensorflow::ops::SparseFillEmptyRowsGrad Class Reference\n\ntensorflow::ops::SparseFillEmptyRowsGrad\n========================================\n\n`#include \u003csparse_ops.h\u003e`\n\nThe gradient of [SparseFillEmptyRows](/versions/r1.15/api_docs/cc/class/tensorflow/ops/sparse-fill-empty-rows#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows).\n\nSummary\n-------\n\nTakes vectors reverse_index_map, shaped `[N]`, and grad_values, shaped `[N_full]`, where `N_full \u003e= N` and copies data into either `d_values` or `d_default_value`. Here `d_values` is shaped `[N]` and `d_default_value` is a scalar.\n\nd_values\\[j\\] = grad_values\\[reverse_index_map\\[j\\]\\] d_default_value = sum_{k : 0 .. N_full - 1} ( grad_values\\[k\\] \\* 1{k not in reverse_index_map})\n\nArguments:\n\n- scope: A [Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- reverse_index_map: 1-D. The reverse index map from [SparseFillEmptyRows](/versions/r1.15/api_docs/cc/class/tensorflow/ops/sparse-fill-empty-rows#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows).\n- grad_values: 1-D. The gradients from backprop.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) d_values: 1-D. The backprop into values.\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) d_default_value: 0-D. The backprop into default_value.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [SparseFillEmptyRowsGrad](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_grad_1ada5dd8406dc685e9cef6fb62d22ef08a)`(const ::`[tensorflow::Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` reverse_index_map, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad_values)` ||\n\n| ### Public attributes ||\n|---------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|\n| [d_default_value](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_grad_1a390e699bba2fa2de13aa830fa180150b) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [d_values](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_grad_1a13ae288ea1b435bc21beaf155bb49a66) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [operation](#classtensorflow_1_1ops_1_1_sparse_fill_empty_rows_grad_1a5d59df27d9ed5efa484e261d96d2fb65) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n\nPublic attributes\n-----------------\n\n### d_default_value\n\n```scdoc\n::tensorflow::Output d_default_value\n``` \n\n### d_values\n\n```scdoc\n::tensorflow::Output d_values\n``` \n\n### operation\n\n```text\nOperation operation\n``` \n\nPublic functions\n----------------\n\n### SparseFillEmptyRowsGrad\n\n```gdscript\n SparseFillEmptyRowsGrad(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input reverse_index_map,\n ::tensorflow::Input grad_values\n)\n```"]]
