Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
aliran tensor:: operasi:: Ubah UkuranArea
#include <image_ops.h> Ubah ukuran images ke size menggunakan interpolasi area.
Ringkasan
Gambar masukan bisa bermacam-macam jenisnya tetapi gambar keluaran selalu mengambang.
Kisaran nilai piksel untuk gambar keluaran mungkin sedikit berbeda dari kisaran nilai piksel untuk gambar masukan karena presisi numerik yang terbatas. Untuk menjamin rentang keluaran, misalnya [0.0, 1.0] , terapkan tf.clip_by_value ke keluaran.
Setiap piksel keluaran dihitung dengan terlebih dahulu mengubah jejak piksel menjadi tensor masukan, lalu merata-ratakan piksel yang berpotongan dengan jejak tersebut. Kontribusi piksel masukan terhadap rata-rata diberi bobot berdasarkan pecahan luas yang memotong tapak. Ini sama dengan INTER_AREA OpenCV.
Argumen:
- ruang lingkup: Objek Lingkup
- gambar: 4-D dengan bentuk
[batch, height, width, channels] . - size: = Tensor 1-D int32 dari 2 elemen:
new_height, new_width . Ukuran baru untuk gambar.
Atribut opsional (lihat Attrs ):
- align_corners: Jika benar, bagian tengah dari 4 piksel sudut tensor masukan dan keluaran akan sejajar, mempertahankan nilai pada piksel sudut. Defaultnya salah.
Pengembalian:
-
Output : 4-D dengan bentuk [batch, new_height, new_width, channels] .
Atribut publik
Fungsi publik
simpul
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operator::tensorflow::Keluaran
operator::tensorflow::Output() const
Fungsi statis publik
Sejajarkan Sudut
Attrs AlignCorners(
bool x
)
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::ResizeArea Class Reference\n\ntensorflow::ops::ResizeArea\n===========================\n\n`#include \u003cimage_ops.h\u003e`\n\nResize `images` to `size` using area interpolation.\n\nSummary\n-------\n\n[Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input) images can be of different types but output images are always float.\n\nThe range of pixel values for the output image might be slightly different from the range for the input image because of limited numerical precision. To guarantee an output range, for example `[0.0, 1.0]`, apply `tf.clip_by_value` to the output.\n\nEach output pixel is computed by first transforming the pixel's footprint into the input tensor and then averaging the pixels that intersect the footprint. An input pixel's contribution to the average is weighted by the fraction of its area that intersects the footprint. This is the same as OpenCV's INTER_AREA.\n\nArguments:\n\n- scope: A [Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- images: 4-D with shape `[batch, height, width, channels]`.\n- size: = A 1-D int32 [Tensor](/versions/r1.15/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor) of 2 elements: `new_height, new_width`. The new size for the images.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resize-area/attrs#structtensorflow_1_1ops_1_1_resize_area_1_1_attrs)):\n\n- align_corners: If true, the centers of the 4 corner pixels of the input and output tensors are aligned, preserving the values at the corner pixels. Defaults to false.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): 4-D with shape `[batch, new_height, new_width, channels]`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [ResizeArea](#classtensorflow_1_1ops_1_1_resize_area_1a48c3b130fbd05acaed9512549485f012)`(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)` images, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` size)` ||\n| [ResizeArea](#classtensorflow_1_1ops_1_1_resize_area_1ac1b5d48c5c77399d5198780d905281d7)`(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)` images, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` size, const `[ResizeArea::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resize-area/attrs#structtensorflow_1_1ops_1_1_resize_area_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_resize_area_1a5cb2a40837fb9d975e2ca454469e5cac) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [resized_images](#classtensorflow_1_1ops_1_1_resize_area_1a64b25c97b7028b2b4c93978f2e957ad4) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|-----------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_resize_area_1abdc62a6906daefaa326cda016f8fbb0c)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_resize_area_1a6e7fba9df05a54b4e0de2d079fa03403)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_resize_area_1a15a700424a492dfe07a1777ddc6146bd)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------|\n| [AlignCorners](#classtensorflow_1_1ops_1_1_resize_area_1ae8ffc21c407e98bddb149275984ed3cf)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resize-area/attrs#structtensorflow_1_1ops_1_1_resize_area_1_1_attrs) |\n\n| ### Structs ||\n|-----------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ResizeArea::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resize-area/attrs) | Optional attribute setters for [ResizeArea](/versions/r1.15/api_docs/cc/class/tensorflow/ops/resize-area#classtensorflow_1_1ops_1_1_resize_area). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\n### resized_images\n\n```scdoc\n::tensorflow::Output resized_images\n``` \n\nPublic functions\n----------------\n\n### ResizeArea\n\n```gdscript\n ResizeArea(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input images,\n ::tensorflow::Input size\n)\n``` \n\n### ResizeArea\n\n```gdscript\n ResizeArea(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input images,\n ::tensorflow::Input size,\n const ResizeArea::Attrs & attrs\n)\n``` \n\n### node\n\n```gdscript\n::tensorflow::Node * node() const \n``` \n\n### operator::tensorflow::Input\n\n```gdscript\n operator::tensorflow::Input() const \n``` \n\n### operator::tensorflow::Output\n\n```gdscript\n operator::tensorflow::Output() const \n``` \n\nPublic static functions\n-----------------------\n\n### AlignCorners\n\n```text\nAttrs AlignCorners(\n bool x\n)\n```"]]
