@spec blobFromImage(Keyword.t()) :: any() | {:error, String.t()}

@spec blobFromImage(Evision.Mat.maybe_mat_in()) ::
  Evision.Mat.t() | {:error, String.t()}

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.

Positional Arguments

• image: Evision.Mat.

  input image (with 1-, 3- or 4-channels).

Keyword Arguments

• scalefactor: double.

  multiplier for @p images values.

• size: Size.

  spatial size for output image

• mean: Evision.scalar().

  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.

• swapRB: bool.

  flag which indicates that swap first and last channels in 3-channel image is necessary.

• crop: bool.

  flag which indicates whether image will be cropped after resize or not

• ddepth: integer().

  Depth of output blob. Choose CV_32F or CV_8U.

Return

• retval: Evision.Mat.t()

@details if @p crop is true, input image is resized so one side after resize is equal to corresponding 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.

Python prototype (for reference only):

blobFromImage(image[, scalefactor[, size[, mean[, swapRB[, crop[, ddepth]]]]]]) -> retval

@spec blobFromImage(
  Evision.Mat.maybe_mat_in(),
  [
    crop: term(),
    ddepth: term(),
    mean: term(),
    scalefactor: term(),
    size: term(),
    swapRB: term()
  ]
  | nil
) :: Evision.Mat.t() | {:error, String.t()}

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.

Positional Arguments

• image: Evision.Mat.

  input image (with 1-, 3- or 4-channels).

Keyword Arguments

• scalefactor: double.

  multiplier for @p images values.

• size: Size.

  spatial size for output image

• mean: Evision.scalar().

  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.

• swapRB: bool.

  flag which indicates that swap first and last channels in 3-channel image is necessary.

• crop: bool.

  flag which indicates whether image will be cropped after resize or not

• ddepth: integer().

  Depth of output blob. Choose CV_32F or CV_8U.

Return

• retval: Evision.Mat.t()

@details if @p crop is true, input image is resized so one side after resize is equal to corresponding 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.

Python prototype (for reference only):

blobFromImage(image[, scalefactor[, size[, mean[, swapRB[, crop[, ddepth]]]]]]) -> retval

@spec blobFromImages(Keyword.t()) :: any() | {:error, String.t()}

@spec blobFromImages([Evision.Mat.maybe_mat_in()]) ::
  Evision.Mat.t() | {:error, String.t()}

Creates 4-dimensional blob from series of images. Optionally resizes and crops @p images from center, subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.

Positional Arguments

• images: [Evision.Mat].

  input images (all with 1-, 3- or 4-channels).

Keyword Arguments

• scalefactor: double.

  multiplier for @p images values.

• size: Size.

  spatial size for output image

• mean: Evision.scalar().

  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.

• swapRB: bool.

  flag which indicates that swap first and last channels in 3-channel image is necessary.

• crop: bool.

  flag which indicates whether image will be cropped after resize or not

• ddepth: integer().

  Depth of output blob. Choose CV_32F or CV_8U.

Return

• retval: Evision.Mat.t()

@details if @p crop is true, input image is resized so one side after resize is equal to corresponding 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.

Python prototype (for reference only):

blobFromImages(images[, scalefactor[, size[, mean[, swapRB[, crop[, ddepth]]]]]]) -> retval

@spec blobFromImages(
  [Evision.Mat.maybe_mat_in()],
  [
    crop: term(),
    ddepth: term(),
    mean: term(),
    scalefactor: term(),
    size: term(),
    swapRB: term()
  ]
  | nil
) :: Evision.Mat.t() | {:error, String.t()}

Creates 4-dimensional blob from series of images. Optionally resizes and crops @p images from center, subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.

Positional Arguments

• images: [Evision.Mat].

  input images (all with 1-, 3- or 4-channels).

Keyword Arguments

• scalefactor: double.

  multiplier for @p images values.

• size: Size.

  spatial size for output image

• mean: Evision.scalar().

  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.

• swapRB: bool.

  flag which indicates that swap first and last channels in 3-channel image is necessary.

• crop: bool.

  flag which indicates whether image will be cropped after resize or not

• ddepth: integer().

  Depth of output blob. Choose CV_32F or CV_8U.

Return

• retval: Evision.Mat.t()

@details if @p crop is true, input image is resized so one side after resize is equal to corresponding 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.

Python prototype (for reference only):

blobFromImages(images[, scalefactor[, size[, mean[, swapRB[, crop[, ddepth]]]]]]) -> retval

@spec blobFromImagesWithParams(Keyword.t()) :: any() | {:error, String.t()}

@spec blobFromImagesWithParams([Evision.Mat.maybe_mat_in()]) ::
  Evision.Mat.t() | {:error, String.t()}

blobFromImagesWithParams

Positional Arguments

• images: [Evision.Mat]

Keyword Arguments

• param: Image2BlobParams.

Return

• blob: Evision.Mat.t().

Has overloading in C++

Python prototype (for reference only):

blobFromImagesWithParams(images[, blob[, param]]) -> blob

@spec blobFromImagesWithParams([Evision.Mat.maybe_mat_in()], [{:param, term()}] | nil) ::
  Evision.Mat.t() | {:error, String.t()}

blobFromImagesWithParams

Positional Arguments

• images: [Evision.Mat]

Keyword Arguments

• param: Image2BlobParams.

Return

• blob: Evision.Mat.t().

Has overloading in C++

Python prototype (for reference only):

blobFromImagesWithParams(images[, blob[, param]]) -> blob

@spec blobFromImageWithParams(Keyword.t()) :: any() | {:error, String.t()}

@spec blobFromImageWithParams(Evision.Mat.maybe_mat_in()) ::
  Evision.Mat.t() | {:error, String.t()}

blobFromImageWithParams

Positional Arguments

• image: Evision.Mat

Keyword Arguments

• param: Image2BlobParams.

Return

• blob: Evision.Mat.t().

Has overloading in C++

Python prototype (for reference only):

blobFromImageWithParams(image[, blob[, param]]) -> blob

@spec blobFromImageWithParams(Evision.Mat.maybe_mat_in(), [{:param, term()}] | nil) ::
  Evision.Mat.t() | {:error, String.t()}

blobFromImageWithParams

Positional Arguments

• image: Evision.Mat

Keyword Arguments

• param: Image2BlobParams.

Return

• blob: Evision.Mat.t().

Has overloading in C++

Python prototype (for reference only):

blobFromImageWithParams(image[, blob[, param]]) -> blob

@spec getAvailableTargets(Keyword.t()) :: any() | {:error, String.t()}

@spec getAvailableTargets(Evision.DNN.Backend.enum()) ::
  [Evision.DNN.Target.enum()] | {:error, String.t()}

getAvailableTargets

Positional Arguments

• be: dnn_Backend

Return

• retval: [Target]

Python prototype (for reference only):

getAvailableTargets(be) -> retval

@spec getInferenceEngineBackendType() :: binary() | {:error, String.t()}

Returns Inference Engine internal backend API.

Return

• retval: String

See values of CV_DNN_BACKEND_INFERENCE_ENGINE_* macros. OPENCV_DNN_BACKEND_INFERENCE_ENGINE_TYPE runtime parameter (environment variable) is ignored since 4.6.0. @deprecated

Python prototype (for reference only):

getInferenceEngineBackendType() -> retval

@spec getInferenceEngineCPUType() :: binary() | {:error, String.t()}

Returns Inference Engine CPU type.

Return

• retval: String

Specify OpenVINO plugin: CPU or ARM.

Python prototype (for reference only):

getInferenceEngineCPUType() -> retval

@spec getInferenceEngineVPUType() :: binary() | {:error, String.t()}

Returns Inference Engine VPU type.

Return

• retval: String

See values of CV_DNN_INFERENCE_ENGINE_VPU_TYPE_* macros.

Python prototype (for reference only):

getInferenceEngineVPUType() -> retval

@spec imagesFromBlob(Keyword.t()) :: any() | {:error, String.t()}

@spec imagesFromBlob(Evision.Mat.maybe_mat_in()) ::
  [Evision.Mat.t()] | {:error, String.t()}

Parse a 4D blob and output the images it contains as 2D arrays through a simpler data structure (std::vector<cv::Mat>).

Positional Arguments

• blob_: Evision.Mat.

  4 dimensional array (images, channels, height, width) in floating point precision (CV_32F) from which you would like to extract the images.

Return

• images_: [Evision.Mat].

  array of 2D Mat containing the images extracted from the blob in floating point precision (CV_32F). They are non normalized neither mean added. The number of returned images equals the first dimension of the blob (batch size). Every image has a number of channels equals to the second dimension of the blob (depth).

Python prototype (for reference only):

imagesFromBlob(blob_[, images_]) -> images_

@spec imagesFromBlob(Evision.Mat.maybe_mat_in(), [{atom(), term()}, ...] | nil) ::
  [Evision.Mat.t()] | {:error, String.t()}

Parse a 4D blob and output the images it contains as 2D arrays through a simpler data structure (std::vector<cv::Mat>).

Positional Arguments

• blob_: Evision.Mat.

  4 dimensional array (images, channels, height, width) in floating point precision (CV_32F) from which you would like to extract the images.

Return

• images_: [Evision.Mat].

  array of 2D Mat containing the images extracted from the blob in floating point precision (CV_32F). They are non normalized neither mean added. The number of returned images equals the first dimension of the blob (batch size). Every image has a number of channels equals to the second dimension of the blob (depth).

Python prototype (for reference only):

imagesFromBlob(blob_[, images_]) -> images_

@spec nmsBoxes(
  [{number(), number(), number(), number()}] | Evision.Mat.t() | Nx.Tensor.t(),
  [number()],
  number(),
  number()
) :: [integer()] | {:error, String.t()}

Performs non maximum suppression given boxes and corresponding scores.

Positional Arguments

• bboxes: [Rect2d], Nx.Tensor.t(), Evision.Mat.t()..

  a set of bounding boxes to apply NMS.

• scores: [float].

  a set of corresponding confidences.

• score_threshold: float.

  a threshold used to filter boxes by score.

• nms_threshold: float.

  a threshold used in non maximum suppression.

Keyword Arguments

• eta: float.

  a coefficient in adaptive threshold formula: $nmsthreshold{i+1}=etacdot nms_threshold_i$.

• top_k: int.

  if >0, keep at most @p top_k picked indices.

Return

• indices: [int].

  the kept indices of bboxes after NMS.

Python prototype (for reference only):

NMSBoxes(bboxes, scores, score_threshold, nms_threshold[, eta[, top_k]]) -> indices

@spec nmsBoxes(
  [{number(), number(), number(), number()}] | Evision.Mat.t() | Nx.Tensor.t(),
  [number()],
  number(),
  number(),
  [eta: term(), top_k: term()] | nil
) :: [integer()] | {:error, String.t()}

Performs non maximum suppression given boxes and corresponding scores.

Positional Arguments

• bboxes: [Rect2d], Nx.Tensor.t(), Evision.Mat.t().

  a set of bounding boxes to apply NMS.

• scores: [float].

  a set of corresponding confidences.

• score_threshold: float.

  a threshold used to filter boxes by score.

• nms_threshold: float.

  a threshold used in non maximum suppression.

Keyword Arguments

• eta: float.

  a coefficient in adaptive threshold formula: $nmsthreshold{i+1}=etacdot nms_threshold_i$.

• top_k: int.

  if >0, keep at most @p top_k picked indices.

Return

• indices: [int].

  the kept indices of bboxes after NMS.

Python prototype (for reference only):

NMSBoxes(bboxes, scores, score_threshold, nms_threshold[, eta[, top_k]]) -> indices

@spec nmsBoxesBatched(
  [{number(), number(), number(), number()}],
  [number()],
  [integer()],
  number(),
  number()
) :: [integer()] | {:error, String.t()}

Performs batched non maximum suppression on given boxes and corresponding scores across different classes.

Positional Arguments

• bboxes: [Rect2d], Nx.Tensor.t(), Evision.Mat.t().

  a set of bounding boxes to apply NMS.

• scores: [float].

  a set of corresponding confidences.

• class_ids: [int].

  a set of corresponding class ids. Ids are integer and usually start from 0.

• score_threshold: float.

  a threshold used to filter boxes by score.

• nms_threshold: float.

  a threshold used in non maximum suppression.

Keyword Arguments

• eta: float.

  a coefficient in adaptive threshold formula: $nmsthreshold{i+1}=etacdot nms_threshold_i$.

• top_k: int.

  if >0, keep at most @p top_k picked indices.

Return

• indices: [int].

  the kept indices of bboxes after NMS.

Python prototype (for reference only):

NMSBoxesBatched(bboxes, scores, class_ids, score_threshold, nms_threshold[, eta[, top_k]]) -> indices

@spec nmsBoxesBatched(
  [{number(), number(), number(), number()}],
  [number()],
  [integer()],
  number(),
  number(),
  [eta: term(), top_k: term()] | nil
) :: [integer()] | {:error, String.t()}

Performs batched non maximum suppression on given boxes and corresponding scores across different classes.

Positional Arguments

• bboxes: [Rect2d], Nx.Tensor.t(), Evision.Mat.t().

  a set of bounding boxes to apply NMS.

• scores: [float].

  a set of corresponding confidences.

• class_ids: [int].

  a set of corresponding class ids. Ids are integer and usually start from 0.

• score_threshold: float.

  a threshold used to filter boxes by score.

• nms_threshold: float.

  a threshold used in non maximum suppression.

Keyword Arguments

• eta: float.

  a coefficient in adaptive threshold formula: $nmsthreshold{i+1}=etacdot nms_threshold_i$.

• top_k: int.

  if >0, keep at most @p top_k picked indices.

Return

• indices: [int].

  the kept indices of bboxes after NMS.

Python prototype (for reference only):

NMSBoxesBatched(bboxes, scores, class_ids, score_threshold, nms_threshold[, eta[, top_k]]) -> indices

@spec nmsBoxesRotated(
  [{{number(), number()}, {number(), number()}, number()}],
  [number()],
  number(),
  number()
) :: [integer()] | {:error, String.t()}

NMSBoxesRotated

Positional Arguments

• bboxes: [{centre={x, y}, size={s1, s2}, angle}]
• scores: [float]
• score_threshold: float
• nms_threshold: float

Keyword Arguments

• eta: float.
• top_k: integer().

Return

• indices: [integer()]

Python prototype (for reference only):

NMSBoxesRotated(bboxes, scores, score_threshold, nms_threshold[, eta[, top_k]]) -> indices

@spec nmsBoxesRotated(
  [{{number(), number()}, {number(), number()}, number()}],
  [number()],
  number(),
  number(),
  [eta: term(), top_k: term()] | nil
) :: [integer()] | {:error, String.t()}

NMSBoxesRotated

Positional Arguments

• bboxes: [{centre={x, y}, size={s1, s2}, angle}]
• scores: [float]
• score_threshold: float
• nms_threshold: float

Keyword Arguments

• eta: float.
• top_k: integer().

Return

• indices: [integer()]

Python prototype (for reference only):

NMSBoxesRotated(bboxes, scores, score_threshold, nms_threshold[, eta[, top_k]]) -> indices

@spec readNet(Keyword.t()) :: any() | {:error, String.t()}

@spec readNet(binary()) :: Evision.DNN.Net.t() | {:error, String.t()}

Read deep learning network represented in one of the supported formats.

Positional Arguments

• model: String.Binary file contains trained weights. The following file extensions are expected for models from different frameworks:
  • *.pb (TensorFlow, https://www.tensorflow.org/)

    • *.bin | *.onnx (OpenVINO, https://software.intel.com/openvino-toolkit)

      • *.onnx (ONNX, https://onnx.ai/)

Keyword Arguments

• config: String.

  Text file contains network configuration. It could be a file with the following extensions:

  • *.pbtxt (TensorFlow, https://www.tensorflow.org/)
    • *.xml (OpenVINO, https://software.intel.com/openvino-toolkit)

• framework: String.

  Explicit framework name tag to determine a format.

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now. Use ENGINE_CLASSIC if you want to use other back-ends.

Return

• retval: Evision.DNN.Net.t()

@returns Net object. This function automatically detects an origin framework of trained model and calls an appropriate function such @ref readNetFromTensorflow, @ref readNetFromONNX. An order of @p model and @p config arguments does not matter.

Python prototype (for reference only):

readNet(model[, config[, framework[, engine]]]) -> retval

@spec readNet(binary(), [config: term(), engine: term(), framework: term()] | nil) ::
  Evision.DNN.Net.t() | {:error, String.t()}

@spec readNet(binary(), binary()) :: Evision.DNN.Net.t() | {:error, String.t()}

Variant 1:

Read deep learning network represented in one of the supported formats.

Positional Arguments

• framework: String.

  Name of origin framework.

• bufferModel: [uchar].

  A buffer with a content of binary file with weights

Keyword Arguments

• bufferConfig: [uchar].

  A buffer with a content of text file contains network configuration.

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now. Use ENGINE_CLASSIC if you want to use other back-ends.

Return

• retval: Evision.DNN.Net.t()

@details This is an overloaded member function, provided for convenience.

      It differs from the above function only in what argument(s) it accepts.

@returns Net object.

Python prototype (for reference only):

readNet(framework, bufferModel[, bufferConfig[, engine]]) -> retval

Variant 2:

Read deep learning network represented in one of the supported formats.

Positional Arguments

• model: String.Binary file contains trained weights. The following file extensions are expected for models from different frameworks:
  • *.pb (TensorFlow, https://www.tensorflow.org/)

    • *.bin | *.onnx (OpenVINO, https://software.intel.com/openvino-toolkit)

      • *.onnx (ONNX, https://onnx.ai/)

Keyword Arguments

• config: String.

  Text file contains network configuration. It could be a file with the following extensions:

  • *.pbtxt (TensorFlow, https://www.tensorflow.org/)
    • *.xml (OpenVINO, https://software.intel.com/openvino-toolkit)

• framework: String.

  Explicit framework name tag to determine a format.

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now. Use ENGINE_CLASSIC if you want to use other back-ends.

Return

• retval: Evision.DNN.Net.t()

@returns Net object. This function automatically detects an origin framework of trained model and calls an appropriate function such @ref readNetFromTensorflow, @ref readNetFromONNX. An order of @p model and @p config arguments does not matter.

Python prototype (for reference only):

readNet(model[, config[, framework[, engine]]]) -> retval

@spec readNet(binary(), binary(), [bufferConfig: term(), engine: term()] | nil) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Read deep learning network represented in one of the supported formats.

Positional Arguments

• framework: String.

  Name of origin framework.

• bufferModel: [uchar].

  A buffer with a content of binary file with weights

Keyword Arguments

• bufferConfig: [uchar].

  A buffer with a content of text file contains network configuration.

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now. Use ENGINE_CLASSIC if you want to use other back-ends.

Return

• retval: Evision.DNN.Net.t()

@details This is an overloaded member function, provided for convenience.

      It differs from the above function only in what argument(s) it accepts.

@returns Net object.

Python prototype (for reference only):

readNet(framework, bufferModel[, bufferConfig[, engine]]) -> retval

@spec readNetFromModelOptimizer(binary()) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Load a network from Intel's Model Optimizer intermediate representation.

Positional Arguments

• xml: String.

  XML configuration file with network's topology.

Keyword Arguments

• bin: String.

  Binary file with trained weights.

Return

• retval: Evision.DNN.Net.t()

@returns Net object. Networks imported from Intel's Model Optimizer are launched in Intel's Inference Engine backend.

Python prototype (for reference only):

readNetFromModelOptimizer(xml[, bin]) -> retval

@spec readNetFromModelOptimizer(binary(), [{:bin, term()}] | nil) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Load a network from Intel's Model Optimizer intermediate representation.

Positional Arguments

• xml: String.

  XML configuration file with network's topology.

Keyword Arguments

• bin: String.

  Binary file with trained weights.

Return

• retval: Evision.DNN.Net.t()

@returns Net object. Networks imported from Intel's Model Optimizer are launched in Intel's Inference Engine backend.

Python prototype (for reference only):

readNetFromModelOptimizer(xml[, bin]) -> retval

@spec readNetFromModelOptimizerBuffer(binary(), binary()) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Load a network from Intel's Model Optimizer intermediate representation.

Positional Arguments

• bufferModelConfig: [uchar].

  Buffer contains XML configuration with network's topology.

• bufferWeights: [uchar].

  Buffer contains binary data with trained weights.

Return

• retval: Evision.DNN.Net.t()

@returns Net object. Networks imported from Intel's Model Optimizer are launched in Intel's Inference Engine backend.

Python prototype (for reference only):

readNetFromModelOptimizer(bufferModelConfig, bufferWeights) -> retval

@spec readNetFromONNX(binary()) :: Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model <a href="https://onnx.ai/">ONNX</a>.

Positional Arguments

• onnxFile: String.

  path to the .onnx file with text description of the network architecture.

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Network object that ready to do forward, throw an exception in failure cases.

Python prototype (for reference only):

readNetFromONNX(onnxFile[, engine]) -> retval

@spec readNetFromONNX(binary(), [{:engine, term()}] | nil) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model <a href="https://onnx.ai/">ONNX</a>.

Positional Arguments

• onnxFile: String.

  path to the .onnx file with text description of the network architecture.

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Network object that ready to do forward, throw an exception in failure cases.

Python prototype (for reference only):

readNetFromONNX(onnxFile[, engine]) -> retval

@spec readNetFromONNXBuffer(Keyword.t()) :: any() | {:error, String.t()}

@spec readNetFromONNXBuffer(binary()) :: Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model from <a href="https://onnx.ai/">ONNX</a> in-memory buffer.

Positional Arguments

• buffer: [uchar].

  in-memory buffer that stores the ONNX model bytes.

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Network object that ready to do forward, throw an exception

    in failure cases.

Python prototype (for reference only):

readNetFromONNX(buffer[, engine]) -> retval

@spec readNetFromONNXBuffer(binary(), [{:engine, term()}] | nil) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model from <a href="https://onnx.ai/">ONNX</a> in-memory buffer.

Positional Arguments

• buffer: [uchar].

  in-memory buffer that stores the ONNX model bytes.

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Network object that ready to do forward, throw an exception

    in failure cases.

Python prototype (for reference only):

readNetFromONNX(buffer[, engine]) -> retval

@spec readNetFromTensorflow(binary()) :: Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/">TensorFlow</a> framework's format.

Positional Arguments

• model: String.

  path to the .pb file with binary protobuf description of the network architecture

Keyword Arguments

• config: String.

  path to the .pbtxt file that contains text graph definition in protobuf format. Resulting Net object is built by text graph using weights from a binary one that let us make it more flexible.

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used.

• extraOutputs: [String].

  specify model outputs explicitly, in addition to the outputs the graph analyzer finds. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTensorflow(model[, config[, engine[, extraOutputs]]]) -> retval

@spec readNetFromTensorflow(
  binary(),
  [config: term(), engine: term(), extraOutputs: term()] | nil
) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/">TensorFlow</a> framework's format.

Positional Arguments

• model: String.

  path to the .pb file with binary protobuf description of the network architecture

Keyword Arguments

• config: String.

  path to the .pbtxt file that contains text graph definition in protobuf format. Resulting Net object is built by text graph using weights from a binary one that let us make it more flexible.

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used.

• extraOutputs: [String].

  specify model outputs explicitly, in addition to the outputs the graph analyzer finds. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTensorflow(model[, config[, engine[, extraOutputs]]]) -> retval

@spec readNetFromTensorflowBuffer(Keyword.t()) :: any() | {:error, String.t()}

@spec readNetFromTensorflowBuffer(binary()) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/">TensorFlow</a> framework's format.

Positional Arguments

• bufferModel: [uchar].

  buffer containing the content of the pb file

Keyword Arguments

• bufferConfig: [uchar].

  buffer containing the content of the pbtxt file

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used.

• extraOutputs: [String].

  specify model outputs explicitly, in addition to the outputs the graph analyzer finds. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTensorflow(bufferModel[, bufferConfig[, engine[, extraOutputs]]]) -> retval

@spec readNetFromTensorflowBuffer(
  binary(),
  [bufferConfig: term(), engine: term(), extraOutputs: term()] | nil
) :: Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/">TensorFlow</a> framework's format.

Positional Arguments

• bufferModel: [uchar].

  buffer containing the content of the pb file

Keyword Arguments

• bufferConfig: [uchar].

  buffer containing the content of the pbtxt file

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used.

• extraOutputs: [String].

  specify model outputs explicitly, in addition to the outputs the graph analyzer finds. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTensorflow(bufferModel[, bufferConfig[, engine[, extraOutputs]]]) -> retval

@spec readNetFromTFLite(binary()) :: Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/lite">TFLite</a> framework's format.

Positional Arguments

• model: String.

  path to the .tflite file with binary flatbuffers description of the network architecture

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTFLite(model[, engine]) -> retval

@spec readNetFromTFLite(binary(), [{:engine, term()}] | nil) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/lite">TFLite</a> framework's format.

Positional Arguments

• model: String.

  path to the .tflite file with binary flatbuffers description of the network architecture

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTFLite(model[, engine]) -> retval

@spec readNetFromTFLiteBuffer(Keyword.t()) :: any() | {:error, String.t()}

@spec readNetFromTFLiteBuffer(binary()) :: Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/lite">TFLite</a> framework's format.

Positional Arguments

• bufferModel: [uchar].

  buffer containing the content of the tflite file

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTFLite(bufferModel[, engine]) -> retval

@spec readNetFromTFLiteBuffer(binary(), [{:engine, term()}] | nil) ::
  Evision.DNN.Net.t() | {:error, String.t()}

Reads a network model stored in <a href="https://www.tensorflow.org/lite">TFLite</a> framework's format.

Positional Arguments

• bufferModel: [uchar].

  buffer containing the content of the tflite file

Keyword Arguments

• engine: integer().

  select DNN engine to be used. With auto selection the new engine is used first and falls back to classic. Please pay attention that the new DNN does not support non-CPU back-ends for now.

Return

• retval: Evision.DNN.Net.t()

@returns Net object.

Python prototype (for reference only):

readNetFromTFLite(bufferModel[, engine]) -> retval

@spec readTensorFromONNX(Keyword.t()) :: any() | {:error, String.t()}

@spec readTensorFromONNX(binary()) :: Evision.Mat.t() | {:error, String.t()}

Creates blob from .pb file.

Positional Arguments

• path: String.

  to the .pb file with input tensor.

Return

• retval: Evision.Mat.t()

@returns Mat.

Python prototype (for reference only):

readTensorFromONNX(path) -> retval

@spec releaseHDDLPlugin() :: :ok | {:error, String.t()}

Release a HDDL plugin.

Python prototype (for reference only):

releaseHDDLPlugin() -> None

@spec resetMyriadDevice() :: :ok | {:error, String.t()}

Release a Myriad device (binded by OpenCV).

Single Myriad device cannot be shared across multiple processes which uses Inference Engine's Myriad plugin.

Python prototype (for reference only):

resetMyriadDevice() -> None

@spec setInferenceEngineBackendType(Keyword.t()) :: any() | {:error, String.t()}

@spec setInferenceEngineBackendType(binary()) :: binary() | {:error, String.t()}

Specify Inference Engine internal backend API.

Positional Arguments

• newBackendType: String

Return

• retval: String

See values of CV_DNN_BACKEND_INFERENCE_ENGINE_* macros. @returns previous value of internal backend API @deprecated

Python prototype (for reference only):

setInferenceEngineBackendType(newBackendType) -> retval

@spec softNMSBoxes(
  [{number(), number(), number(), number()}],
  [number()],
  number(),
  number()
) ::
  {[number()], [integer()]} | {:error, String.t()}

Performs soft non maximum suppression given boxes and corresponding scores. Reference: https://arxiv.org/abs/1704.04503

Positional Arguments

• bboxes: [Rect], Nx.Tensor.t(), Evision.Mat.t()..

  a set of bounding boxes to apply Soft NMS.

• scores: [float].

  a set of corresponding confidences.

• score_threshold: float.

  a threshold used to filter boxes by score.

• nms_threshold: float.

  a threshold used in non maximum suppression.

Keyword Arguments

• top_k: size_t.

  keep at most @p top_k picked indices.

• sigma: float.

  parameter of Gaussian weighting.

• method: SoftNMSMethod.

  Gaussian or linear.

Return

• updated_scores: [float].

  a set of corresponding updated confidences.

• indices: [int].

  the kept indices of bboxes after NMS.

@see SoftNMSMethod

Python prototype (for reference only):

softNMSBoxes(bboxes, scores, score_threshold, nms_threshold[, top_k[, sigma[, method]]]) -> updated_scores, indices

@spec softNMSBoxes(
  [{number(), number(), number(), number()}],
  [number()],
  number(),
  number(),
  [top_k: term(), sigma: term(), method: term()] | nil
) :: {[number()], [integer()]} | {:error, String.t()}

Performs soft non maximum suppression given boxes and corresponding scores. Reference: https://arxiv.org/abs/1704.04503

Positional Arguments

• bboxes: [Rect], Nx.Tensor.t(), Evision.Mat.t()..

  a set of bounding boxes to apply Soft NMS.

• scores: [float].

  a set of corresponding confidences.

• score_threshold: float.

  a threshold used to filter boxes by score.

• nms_threshold: float.

  a threshold used in non maximum suppression.

Keyword Arguments

• top_k: size_t.

  keep at most @p top_k picked indices.

• sigma: float.

  parameter of Gaussian weighting.

• method: SoftNMSMethod.

  Gaussian or linear.

Return

• updated_scores: [float].

  a set of corresponding updated confidences.

• indices: [int].

  the kept indices of bboxes after NMS.

@see SoftNMSMethod

Python prototype (for reference only):

softNMSBoxes(bboxes, scores, score_threshold, nms_threshold[, top_k[, sigma[, method]]]) -> updated_scores, indices

@spec writeTextGraph(binary(), binary()) :: :ok | {:error, String.t()}

Create a text representation for a binary network stored in protocol buffer format.

Positional Arguments

• model: String.

  A path to binary network.

• output: String.

  A path to output text file to be created.

Note: To reduce output file size, trained weights are not included.

Python prototype (for reference only):

writeTextGraph(model, output) -> None