Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
tensoreflusso:: ops:: Ritaglia e ridimensiona l'immagine del grado
#include <image_ops.h> Calcola il gradiente dell'operazione crop_and_resize rispetto al tensore dell'immagine in input.
Riepilogo
Argomenti:
- scope: un oggetto Scope
- grads: un tensore di forma 4-D
[num_boxes, crop_height, crop_width, depth] . - boxs: un tensore 2-D di forma
[num_boxes, 4] . L' i -esima riga del tensore specifica le coordinate di un riquadro nell'immagine box_ind[i] ed è specificata in coordinate normalizzate [y1, x1, y2, x2] . Un valore di coordinata normalizzato di y viene mappato alla coordinata dell'immagine in y * (image_height - 1) , in modo che l'intervallo [0, 1] dell'altezza dell'immagine normalizzata venga mappato su `[0, image_height - 1] nelle coordinate dell'altezza dell'immagine. Consentiamo y1 > y2, nel qual caso il ritaglio campionato è una versione capovolta verso l'alto dell'immagine originale. La dimensione della larghezza viene trattata in modo simile. Sono consentite coordinate normalizzate esterne all'intervallo [0, 1] , nel qual caso utilizziamo extrapolation_value per estrapolare i valori dell'immagine di input. - box_ind: un tensore 1-D di forma
[num_boxes] con valori int32 in [0, batch) . Il valore di box_ind[i] specifica l'immagine a cui si riferisce l' i -esimo box. - image_size: un tensore 1-D con valore
[batch, image_height, image_width, depth] contenente la dimensione dell'immagine originale. Sia image_height che image_width devono essere positivi.
Attributi facoltativi (vedi Attrs ):
- metodo: una stringa che specifica il metodo di interpolazione. Per ora è supportato solo "bilineare".
Resi:
-
Output : un tensore 4-D di forma [batch, image_height, image_width, depth] .
Costruttori e distruttori |
|---|
CropAndResizeGradImage (const :: tensorflow::Scope & scope, :: tensorflow::Input grads, :: tensorflow::Input boxes, :: tensorflow::Input box_ind, :: tensorflow::Input image_size, DataType T)
|
CropAndResizeGradImage (const :: tensorflow::Scope & scope, :: tensorflow::Input grads, :: tensorflow::Input boxes, :: tensorflow::Input box_ind, :: tensorflow::Input image_size, DataType T, const CropAndResizeGradImage::Attrs & attrs)
|
Funzioni pubbliche statiche |
|---|
Method (StringPiece x) | |
Attributi pubblici
Funzioni pubbliche
nodo
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operatore::tensorflow::Output
operator::tensorflow::Output() const
Funzioni pubbliche statiche
Metodo
Attrs Method(
StringPiece x
)
Salvo quando diversamente specificato, i contenuti di questa pagina sono concessi in base alla licenza Creative Commons Attribution 4.0, mentre gli esempi di codice sono concessi in base alla licenza Apache 2.0. Per ulteriori dettagli, consulta le norme del sito di Google Developers. Java è un marchio registrato di Oracle e/o delle sue consociate.
Ultimo aggiornamento 2025-07-26 UTC.
[null,null,["Ultimo aggiornamento 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::CropAndResizeGradImage Class Reference\n\ntensorflow::ops::CropAndResizeGradImage\n=======================================\n\n`#include \u003cimage_ops.h\u003e`\n\nComputes the gradient of the crop_and_resize op wrt the input image tensor.\n\nSummary\n-------\n\nArguments:\n\n- scope: A [Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- grads: A 4-D tensor of shape `[num_boxes, crop_height, crop_width, depth]`.\n- boxes: A 2-D tensor of shape `[num_boxes, 4]`. The `i`-th row of the tensor specifies the coordinates of a box in the `box_ind[i]` image and is specified in normalized coordinates `[y1, x1, y2, x2]`. A normalized coordinate value of `y` is mapped to the image coordinate at `y * (image_height - 1)`, so as the `[0, 1]` interval of normalized image height is mapped to \\`\\[0, image_height - 1\\] in image height coordinates. We do allow y1 \\\u003e y2, in which case the sampled crop is an up-down flipped version of the original image. The width dimension is treated similarly. Normalized coordinates outside the `[0, 1]` range are allowed, in which case we use `extrapolation_value` to extrapolate the input image values.\n- box_ind: A 1-D tensor of shape `[num_boxes]` with int32 values in `[0, batch)`. The value of `box_ind[i]` specifies the image that the `i`-th box refers to.\n- image_size: A 1-D tensor with value `[batch, image_height, image_width, depth]` containing the original image size. Both `image_height` and `image_width` need to be positive.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/crop-and-resize-grad-image/attrs#structtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1_1_attrs)):\n\n- method: A string specifying the interpolation method. Only 'bilinear' is supported for now.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): A 4-D tensor of shape `[batch, image_height, image_width, depth]`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [CropAndResizeGradImage](#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1a542871b76c83a2a8ae095c5ade81ab0e)`(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)` grads, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` boxes, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` box_ind, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` image_size, DataType T)` ||\n| [CropAndResizeGradImage](#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1a5314c519439a0018be03ae0599c320d3)`(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)` grads, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` boxes, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` box_ind, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` image_size, DataType T, const `[CropAndResizeGradImage::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/crop-and-resize-grad-image/attrs#structtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|--------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1ad757af122f700a9ab5acbd38629f83fb) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1adc227b21eb0d9d4ca672f34f67b7943d) | `::`[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_crop_and_resize_grad_image_1a614b37524e5b31e34837f59518d54830)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1a561ea8804d44d30b5d50d84b6619a89c)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1a189d45da47ace193a132f998417286d2)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|----------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Method](#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1a10a7af8fef715e541d4c1c1472871fa5)`(StringPiece x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/crop-and-resize-grad-image/attrs#structtensorflow_1_1ops_1_1_crop_and_resize_grad_image_1_1_attrs) |\n\n| ### Structs ||\n|--------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::CropAndResizeGradImage::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/crop-and-resize-grad-image/attrs) | Optional attribute setters for [CropAndResizeGradImage](/versions/r1.15/api_docs/cc/class/tensorflow/ops/crop-and-resize-grad-image#classtensorflow_1_1ops_1_1_crop_and_resize_grad_image). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\n### output\n\n```text\n::tensorflow::Output output\n``` \n\nPublic functions\n----------------\n\n### CropAndResizeGradImage\n\n```gdscript\n CropAndResizeGradImage(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input grads,\n ::tensorflow::Input boxes,\n ::tensorflow::Input box_ind,\n ::tensorflow::Input image_size,\n DataType T\n)\n``` \n\n### CropAndResizeGradImage\n\n```gdscript\n CropAndResizeGradImage(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input grads,\n ::tensorflow::Input boxes,\n ::tensorflow::Input box_ind,\n ::tensorflow::Input image_size,\n DataType T,\n const CropAndResizeGradImage::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### Method\n\n```text\nAttrs Method(\n StringPiece x\n)\n```"]]
