mirror of
https://github.com/opencv/opencv.git
synced 2026-07-30 07:43:03 +04:00
Merge pull request #22750 from zihaomu:improve_blobFromImage
DNN: Add New API blobFromImageParam #22750 The purpose of this PR: 1. Add new API `blobFromImageParam` to extend `blobFromImage` API. It can support the different data layout (NCHW or NHWC), and letter_box. 2. ~~`blobFromImage` can output `CV_16F`~~ ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Zihao Mu
GitHub
@@ -108,6 +108,21 @@ CV__DNN_INLINE_NS_BEGIN
|
||||
DNN_TARGET_NPU,
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Enum of data layout for model inference.
|
||||
* @see Image2BlobParams
|
||||
*/
|
||||
enum DataLayout
|
||||
{
|
||||
DNN_LAYOUT_UNKNOWN = 0,
|
||||
DNN_LAYOUT_ND = 1, //!< OpenCV data layout for 2D data.
|
||||
DNN_LAYOUT_NCHW = 2, //!< OpenCV data layout for 4D data.
|
||||
DNN_LAYOUT_NCDHW = 3, //!< OpenCV data layout for 5D data.
|
||||
DNN_LAYOUT_NHWC = 4, //!< Tensorflow-like data layout for 4D data.
|
||||
DNN_LAYOUT_NDHWC = 5, //!< Tensorflow-like data layout for 5D data.
|
||||
DNN_LAYOUT_PLANAR = 6, //!< Tensorflow-like data layout, it should only be used at tf or tflite model parsing.
|
||||
};
|
||||
|
||||
CV_EXPORTS std::vector< std::pair<Backend, Target> > getAvailableBackends();
|
||||
CV_EXPORTS_W std::vector<Target> getAvailableTargets(dnn::Backend be);
|
||||
|
||||
@@ -1111,10 +1126,10 @@ CV__DNN_INLINE_NS_BEGIN
|
||||
/** @brief Creates 4-dimensional blob from image. Optionally resizes and crops @p image from center,
|
||||
* subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.
|
||||
* @param image input image (with 1-, 3- or 4-channels).
|
||||
* @param scalefactor multiplier for @p images values.
|
||||
* @param size spatial size for output image
|
||||
* @param mean scalar with mean values which are subtracted from channels. Values are intended
|
||||
* to be in (mean-R, mean-G, mean-B) order if @p image has BGR ordering and @p swapRB is true.
|
||||
* @param scalefactor multiplier for @p image values.
|
||||
* @param swapRB flag which indicates that swap first and last channels
|
||||
* in 3-channel image is necessary.
|
||||
* @param crop flag which indicates whether image will be cropped after resize or not
|
||||
@@ -1123,6 +1138,9 @@ CV__DNN_INLINE_NS_BEGIN
|
||||
* dimension in @p size and another one is equal or larger. Then, crop from the center is performed.
|
||||
* If @p crop is false, direct resize without cropping and preserving aspect ratio is performed.
|
||||
* @returns 4-dimensional Mat with NCHW dimensions order.
|
||||
*
|
||||
* @note
|
||||
* The order and usage of `scalefactor` and `mean` are (input - mean) * scalefactor.
|
||||
*/
|
||||
CV_EXPORTS_W Mat blobFromImage(InputArray image, double scalefactor=1.0, const Size& size = Size(),
|
||||
const Scalar& mean = Scalar(), bool swapRB=false, bool crop=false,
|
||||
@@ -1153,6 +1171,9 @@ CV__DNN_INLINE_NS_BEGIN
|
||||
* dimension in @p size and another one is equal or larger. Then, crop from the center is performed.
|
||||
* If @p crop is false, direct resize without cropping and preserving aspect ratio is performed.
|
||||
* @returns 4-dimensional Mat with NCHW dimensions order.
|
||||
*
|
||||
* @note
|
||||
* The order and usage of `scalefactor` and `mean` are (input - mean) * scalefactor.
|
||||
*/
|
||||
CV_EXPORTS_W Mat blobFromImages(InputArrayOfArrays images, double scalefactor=1.0,
|
||||
Size size = Size(), const Scalar& mean = Scalar(), bool swapRB=false, bool crop=false,
|
||||
@@ -1167,6 +1188,74 @@ CV__DNN_INLINE_NS_BEGIN
|
||||
const Scalar& mean = Scalar(), bool swapRB=false, bool crop=false,
|
||||
int ddepth=CV_32F);
|
||||
|
||||
/**
|
||||
* @brief Enum of image processing mode.
|
||||
* To facilitate the specialization pre-processing requirements of the dnn model.
|
||||
* For example, the `letter box` often used in the Yolo series of models.
|
||||
* @see Image2BlobParams
|
||||
*/
|
||||
enum ImagePaddingMode
|
||||
{
|
||||
DNN_PMODE_NULL = 0, // !< Default. Resize to required input size without extra processing.
|
||||
DNN_PMODE_CROP_CENTER = 1, // !< Image will be cropped after resize.
|
||||
DNN_PMODE_LETTERBOX = 2, // !< Resize image to the desired size while preserving the aspect ratio of original image.
|
||||
};
|
||||
|
||||
/** @brief Processing params of image to blob.
|
||||
*
|
||||
* It includes all possible image processing operations and corresponding parameters.
|
||||
*
|
||||
* @see blobFromImageWithParams
|
||||
*
|
||||
* @note
|
||||
* The order and usage of `scalefactor` and `mean` are (input - mean) * scalefactor.
|
||||
* The order and usage of `scalefactor`, `size`, `mean`, `swapRB`, and `ddepth` are consistent
|
||||
* with the function of @ref blobFromImage.
|
||||
*/
|
||||
struct CV_EXPORTS_W_SIMPLE Image2BlobParams
|
||||
{
|
||||
CV_WRAP Image2BlobParams();
|
||||
CV_WRAP Image2BlobParams(const Scalar& scalefactor, const Size& size = Size(), const Scalar& mean = Scalar(),
|
||||
bool swapRB = false, int ddepth = CV_32F, DataLayout datalayout = DNN_LAYOUT_NCHW,
|
||||
ImagePaddingMode mode = DNN_PMODE_NULL);
|
||||
|
||||
CV_PROP_RW Scalar scalefactor; //!< scalefactor multiplier for input image values.
|
||||
CV_PROP_RW Size size; //!< Spatial size for output image.
|
||||
CV_PROP_RW Scalar mean; //!< Scalar with mean values which are subtracted from channels.
|
||||
CV_PROP_RW bool swapRB; //!< Flag which indicates that swap first and last channels
|
||||
CV_PROP_RW int ddepth; //!< Depth of output blob. Choose CV_32F or CV_8U.
|
||||
CV_PROP_RW DataLayout datalayout; //!< Order of output dimensions. Choose DNN_LAYOUT_NCHW or DNN_LAYOUT_NHWC.
|
||||
CV_PROP_RW ImagePaddingMode paddingmode; //!< Image padding mode. @see ImagePaddingMode.
|
||||
};
|
||||
|
||||
/** @brief Creates 4-dimensional blob from image with given params.
|
||||
*
|
||||
* @details This function is an extension of @ref blobFromImage to meet more image preprocess needs.
|
||||
* Given input image and preprocessing parameters, and function outputs the blob.
|
||||
*
|
||||
* @param image input image (all with 1-, 3- or 4-channels).
|
||||
* @param param struct of Image2BlobParams, contains all parameters needed by processing of image to blob.
|
||||
* @return 4-dimensional Mat.
|
||||
*/
|
||||
CV_EXPORTS_W Mat blobFromImageWithParams(InputArray image, const Image2BlobParams& param = Image2BlobParams());
|
||||
|
||||
/** @overload */
|
||||
CV_EXPORTS_W void blobFromImageWithParams(InputArray image, OutputArray blob, const Image2BlobParams& param = Image2BlobParams());
|
||||
|
||||
/** @brief Creates 4-dimensional blob from series of images with given params.
|
||||
*
|
||||
* @details This function is an extension of @ref blobFromImages to meet more image preprocess needs.
|
||||
* Given input image and preprocessing parameters, and function outputs the blob.
|
||||
*
|
||||
* @param images input image (all with 1-, 3- or 4-channels).
|
||||
* @param param struct of Image2BlobParams, contains all parameters needed by processing of image to blob.
|
||||
* @returns 4-dimensional Mat.
|
||||
*/
|
||||
CV_EXPORTS_W Mat blobFromImagesWithParams(InputArrayOfArrays images, const Image2BlobParams& param = Image2BlobParams());
|
||||
|
||||
/** @overload */
|
||||
CV_EXPORTS_W void blobFromImagesWithParams(InputArrayOfArrays images, OutputArray blob, const Image2BlobParams& param = Image2BlobParams());
|
||||
|
||||
/** @brief Parse a 4D blob and output the images it contains as 2D arrays through a simpler data structure
|
||||
* (std::vector<cv::Mat>).
|
||||
* @param[in] blob_ 4 dimensional array (images, channels, height, width) in floating point precision (CV_32F) from
|
||||
|
||||
Reference in New Issue
Block a user