View Source Evision.DNN.Net (Evision v0.1.13)
Link to this section Summary
Types
Type that represents an Evision.DNN.Net
struct.
Functions
Connects output of the first layer to input of the second layer.
Dump net to String
Dump net structure, hyperparameters, backend, target and fusion to dot file
Return
- retval:
bool
Returns true if there are no layers in the network.
Enables or disables layer fusion in the network.
Runs forward pass to compute outputs of layers listed in @p outBlobNames.
Runs forward pass to compute outputs of layers listed in @p outBlobNames.
Runs forward pass to compute output of layer with name @p outputName.
Positional Arguments
- netInputShape:
MatShape
Return
- retval:
int64
Has overloading in C++
Positional Arguments
- layerId:
int
- netInputShape:
MatShape
Return
- retval:
int64
Has overloading in C++
Returns input scale and zeropoint for a quantized Net.
Variant 1:
Positional Arguments
- layerName:
String
Return
- retval:
Evision.DNN.Layer
Has overloading in C++
Converts string name of the layer to the integer identifier.
Return
- retval:
std::vector<String>
Python prototype (for reference):
Positional Arguments
- netInputShapes:
[MatShape]
- layerId:
int
Return
- inLayerShapes:
[MatShape]
- outLayerShapes:
[MatShape]
Has overloading in C++
Returns count of layers of specified type.
Positional Arguments
- netInputShape:
MatShape
Return
- layersIds:
[int]
- inLayersShapes:
[[MatShape]]
- outLayersShapes:
[[MatShape]]
Has overloading in C++
Returns list of types for layer used in model.
Positional Arguments
- netInputShape:
MatShape
Return
- weights:
size_t
- blobs:
size_t
Has overloading in C++
Positional Arguments
- layerId:
int
- netInputShape:
MatShape
Return
- weights:
size_t
- blobs:
size_t
Has overloading in C++
Returns output scale and zeropoint for a quantized Net.
Variant 1:
Positional Arguments
- layerName:
String
Keyword Arguments
- numParam:
int
.
Return
- retval:
Evision.Mat
Python prototype (for reference):
Variant 1:
Positional Arguments
- layerName:
String
Keyword Arguments
- numParam:
int
.
Return
- retval:
Evision.Mat
Python prototype (for reference):
Returns overall time for inference and timings (in ticks) for layers.
Returns indexes of layers with unconnected outputs.
Returns names of layers with unconnected outputs.
Returns a quantized Net from a floating-point Net.
Create a network from Intel's Model Optimizer in-memory buffers with intermediate representation (IR).
Compile Halide layers.
Sets the new input value for the network
Sets the new input value for the network
Specify shape of network input.
Sets outputs names of the network input pseudo layer.
Variant 1:
Positional Arguments
- layerName:
String
- numParam:
int
- blob:
Evision.Mat
Python prototype (for reference):
Ask network to use specific computation backend where it supported.
Ask network to make computations on specific target device.
Link to this section Types
@type t() :: %Evision.DNN.Net{ref: reference()}
Type that represents an Evision.DNN.Net
struct.
ref.
reference()
The underlying erlang resource variable.
Link to this section Functions
Connects output of the first layer to input of the second layer.
Positional Arguments
outPin:
String
.descriptor of the first layer output.
inpPin:
String
.descriptor of the second layer input.
Descriptors have the following template <DFN><layer_name>[.input_number]</DFN>:
the first part of the template <DFN>layer_name</DFN> is string name of the added layer. If this part is empty then the network input pseudo layer will be used;
the second optional part of the template <DFN>input_number</DFN> is either number of the layer input, either label one. If this part is omitted then the first layer input will be used.
@see setNetInputs(), Layer::inputNameToIndex(), Layer::outputNameToIndex()
Python prototype (for reference):
connect(outPin, inpPin) -> None
Dump net to String
Return
- retval:
String
@returns String with structure, hyperparameters, backend, target and fusion Call method after setInput(). To see correct backend, target and fusion run after forward().
Python prototype (for reference):
dump() -> retval
Dump net structure, hyperparameters, backend, target and fusion to dot file
Positional Arguments
path:
String
.path to output file with .dot extension
@see dump()
Python prototype (for reference):
dumpToFile(path) -> None
Return
- retval:
bool
Returns true if there are no layers in the network.
Python prototype (for reference):
empty() -> retval
Enables or disables layer fusion in the network.
Positional Arguments
fusion:
bool
.true to enable the fusion, false to disable. The fusion is enabled by default.
Python prototype (for reference):
enableFusion(fusion) -> None
@spec forward(Evision.Net.t(), [{atom(), term()}, ...] | nil) :: [Evision.Mat.t()] | {:error, String.t()}
Runs forward pass to compute outputs of layers listed in @p outBlobNames.
Positional Arguments
outBlobNames:
[String]
.names for layers which outputs are needed to get
Return
outputBlobs:
[Evision.Mat]
.contains blobs for first outputs of specified layers.
Python prototype (for reference):
forward(outBlobNames[, outputBlobs]) -> outputBlobs
@spec forwardAndRetrieve(t(), [binary()]) :: [[Evision.Mat.t()]] | {:error, String.t()}
Runs forward pass to compute outputs of layers listed in @p outBlobNames.
Positional Arguments
outBlobNames:
[String]
.names for layers which outputs are needed to get
Return
outputBlobs:
[[Evision.Mat]]
.contains all output blobs for each layer specified in @p outBlobNames.
Python prototype (for reference):
forwardAndRetrieve(outBlobNames) -> outputBlobs
@spec forwardAsync(t()) :: Evision.AsyncArray.t() | {:error, String.t()}
Runs forward pass to compute output of layer with name @p outputName.
Keyword Arguments
outputName:
String
.name for layer which output is needed to get
Return
- retval:
Evision.AsyncArray
@details By default runs forward pass for the whole network. This is an asynchronous version of forward(const String&). dnn::DNN_BACKEND_INFERENCE_ENGINE backend is required.
Python prototype (for reference):
forwardAsync([, outputName]) -> retval
Positional Arguments
- netInputShape:
MatShape
Return
- retval:
int64
Has overloading in C++
Python prototype (for reference):
getFLOPS(netInputShape) -> retval
Positional Arguments
- layerId:
int
- netInputShape:
MatShape
Return
- retval:
int64
Has overloading in C++
Python prototype (for reference):
getFLOPS(layerId, netInputShape) -> retval
Returns input scale and zeropoint for a quantized Net.
Return
scales:
[float]
.output parameter for returning input scales.
zeropoints:
[int]
.output parameter for returning input zeropoints.
Python prototype (for reference):
getInputDetails() -> scales, zeropoints
@spec getLayer(t(), binary()) :: Evision.DNN.Layer.t() | {:error, String.t()}
@spec getLayer(t(), integer()) :: Evision.DNN.Layer.t() | {:error, String.t()}
@spec getLayer(t(), term()) :: Evision.DNN.Layer.t() | {:error, String.t()}
Variant 1:
Positional Arguments
- layerName:
String
Return
- retval:
Evision.DNN.Layer
Has overloading in C++
@deprecated Use int getLayerId(const String &layer)
Python prototype (for reference):
getLayer(layerName) -> retval
Variant 2:
Returns pointer to layer with specified id or name which the network use.
Positional Arguments
- layerId:
int
Return
- retval:
Evision.DNN.Layer
Python prototype (for reference):
getLayer(layerId) -> retval
Variant 3:
Positional Arguments
- layerId:
LayerId
Return
- retval:
Evision.DNN.Layer
Has overloading in C++
@deprecated to be removed
Python prototype (for reference):
getLayer(layerId) -> retval
Converts string name of the layer to the integer identifier.
Positional Arguments
- layer:
String
Return
- retval:
int
@returns id of the layer, or -1 if the layer wasn't found.
Python prototype (for reference):
getLayerId(layer) -> retval
Return
- retval:
std::vector<String>
Python prototype (for reference):
getLayerNames() -> retval
@spec getLayerShapes(Evision.Net.t(), [{{atom(), term()}}, ...] | nil) :: {[[integer()]], [[integer()]]} | {:error, String.t()}
@spec getLayerShapes(Evision.Net.t(), [{{atom(), term()}}, ...] | nil) :: {[integer()], [[[integer()]]], [[[integer()]]]} | {:error, String.t()}
Positional Arguments
- netInputShapes:
[MatShape]
- layerId:
int
Return
- inLayerShapes:
[MatShape]
- outLayerShapes:
[MatShape]
Has overloading in C++
Python prototype (for reference):
getLayerShapes(netInputShapes, layerId) -> inLayerShapes, outLayerShapes
Returns count of layers of specified type.
Positional Arguments
layerType:
String
.type.
Return
- retval:
int
@returns count of layers
Python prototype (for reference):
getLayersCount(layerType) -> retval
Positional Arguments
- netInputShape:
MatShape
Return
- layersIds:
[int]
- inLayersShapes:
[[MatShape]]
- outLayersShapes:
[[MatShape]]
Has overloading in C++
Python prototype (for reference):
getLayersShapes(netInputShape) -> layersIds, inLayersShapes, outLayersShapes
Returns list of types for layer used in model.
Return
layersTypes:
[String]
.output parameter for returning types.
Python prototype (for reference):
getLayerTypes() -> layersTypes
Positional Arguments
- netInputShape:
MatShape
Return
- weights:
size_t
- blobs:
size_t
Has overloading in C++
Python prototype (for reference):
getMemoryConsumption(netInputShape) -> weights, blobs
@spec getMemoryConsumption(t(), integer(), [integer()]) :: {integer(), integer()} | {:error, String.t()}
Positional Arguments
- layerId:
int
- netInputShape:
MatShape
Return
- weights:
size_t
- blobs:
size_t
Has overloading in C++
Python prototype (for reference):
getMemoryConsumption(layerId, netInputShape) -> weights, blobs
Returns output scale and zeropoint for a quantized Net.
Return
scales:
[float]
.output parameter for returning output scales.
zeropoints:
[int]
.output parameter for returning output zeropoints.
Python prototype (for reference):
getOutputDetails() -> scales, zeropoints
@spec getParam(t(), binary()) :: Evision.Mat.t() | {:error, String.t()}
@spec getParam(t(), integer()) :: Evision.Mat.t() | {:error, String.t()}
Variant 1:
Positional Arguments
- layerName:
String
Keyword Arguments
- numParam:
int
.
Return
- retval:
Evision.Mat
Python prototype (for reference):
getParam(layerName[, numParam]) -> retval
Variant 2:
Returns parameter blob of the layer.
Positional Arguments
layer:
int
.name or id of the layer.
Keyword Arguments
numParam:
int
.index of the layer parameter in the Layer::blobs array.
Return
- retval:
Evision.Mat
@see Layer::blobs
Python prototype (for reference):
getParam(layer[, numParam]) -> retval
@spec getParam(t(), binary(), [{atom(), term()}, ...] | nil) :: Evision.Mat.t() | {:error, String.t()}
@spec getParam(t(), integer(), [{atom(), term()}, ...] | nil) :: Evision.Mat.t() | {:error, String.t()}
Variant 1:
Positional Arguments
- layerName:
String
Keyword Arguments
- numParam:
int
.
Return
- retval:
Evision.Mat
Python prototype (for reference):
getParam(layerName[, numParam]) -> retval
Variant 2:
Returns parameter blob of the layer.
Positional Arguments
layer:
int
.name or id of the layer.
Keyword Arguments
numParam:
int
.index of the layer parameter in the Layer::blobs array.
Return
- retval:
Evision.Mat
@see Layer::blobs
Python prototype (for reference):
getParam(layer[, numParam]) -> retval
Returns overall time for inference and timings (in ticks) for layers.
Return
retval:
int64
timings:
[double]
.vector for tick timings for all layers.
Indexes in returned vector correspond to layers ids. Some layers can be fused with others, in this case zero ticks count will be return for that skipped layers. Supported by DNN_BACKEND_OPENCV on DNN_TARGET_CPU only. @return overall ticks for model inference.
Python prototype (for reference):
getPerfProfile() -> retval, timings
Returns indexes of layers with unconnected outputs.
Return
- retval:
std::vector<int>
FIXIT: Rework API to registerOutput() approach, deprecate this call
Python prototype (for reference):
getUnconnectedOutLayers() -> retval
Returns names of layers with unconnected outputs.
Return
- retval:
std::vector<String>
FIXIT: Rework API to registerOutput() approach, deprecate this call
Python prototype (for reference):
getUnconnectedOutLayersNames() -> retval
Return
- self:
Evision.DNN.Net
Python prototype (for reference):
Net() -> <dnn_Net object>
@spec quantize(t(), [Evision.Mat.maybe_mat_in()], integer(), integer()) :: t() | {:error, String.t()}
Returns a quantized Net from a floating-point Net.
Positional Arguments
calibData:
[Evision.Mat]
.Calibration data to compute the quantization parameters.
inputsDtype:
int
.Datatype of quantized net's inputs. Can be CV_32F or CV_8S.
outputsDtype:
int
.Datatype of quantized net's outputs. Can be CV_32F or CV_8S.
Return
- retval:
Evision.DNN.Net
Python prototype (for reference):
quantize(calibData, inputsDtype, outputsDtype) -> retval
Create a network from Intel's Model Optimizer in-memory buffers with intermediate representation (IR).
Positional Arguments
bufferModelConfig:
[uchar]
.buffer with model's configuration.
bufferWeights:
[uchar]
.buffer with model's trained weights.
Return
- retval:
Evision.DNN.Net
@returns Net object.
Python prototype (for reference):
readFromModelOptimizer(bufferModelConfig, bufferWeights) -> retval
Compile Halide layers.
Positional Arguments
scheduler:
String
.Path to YAML file with scheduling directives.
@see setPreferableBackend/2
Schedule layers that support Halide backend. Then compile them for
specific target. For layers that not represented in scheduling file
or if no manual scheduling used at all, automatic scheduling will be applied.
Python prototype (for reference):
setHalideScheduler(scheduler) -> None
@spec setInput(t(), Evision.Mat.maybe_mat_in()) :: :ok | {:error, String.t()}
Sets the new input value for the network
Positional Arguments
blob:
Evision.Mat
.A new blob. Should have CV_32F or CV_8U depth.
Keyword Arguments
name:
String
.A name of input layer.
scalefactor:
double
.An optional normalization scale.
mean:
Scalar
.An optional mean subtraction values.
@see connect(String, String) to know format of the descriptor. If scale or mean values are specified, a final input blob is computed as: \f[input(n,c,h,w) = scalefactor \times (blob(n,c,h,w) - mean_c)\f]
Python prototype (for reference):
setInput(blob[, name[, scalefactor[, mean]]]) -> None
@spec setInput(t(), Evision.Mat.maybe_mat_in(), [{atom(), term()}, ...] | nil) :: :ok | {:error, String.t()}
Sets the new input value for the network
Positional Arguments
blob:
Evision.Mat
.A new blob. Should have CV_32F or CV_8U depth.
Keyword Arguments
name:
String
.A name of input layer.
scalefactor:
double
.An optional normalization scale.
mean:
Scalar
.An optional mean subtraction values.
@see connect(String, String) to know format of the descriptor. If scale or mean values are specified, a final input blob is computed as: \f[input(n,c,h,w) = scalefactor \times (blob(n,c,h,w) - mean_c)\f]
Python prototype (for reference):
setInput(blob[, name[, scalefactor[, mean]]]) -> None
Specify shape of network input.
Positional Arguments
- inputName:
String
- shape:
MatShape
Python prototype (for reference):
setInputShape(inputName, shape) -> None
Sets outputs names of the network input pseudo layer.
Positional Arguments
- inputBlobNames:
[String]
Each net always has special own the network input pseudo layer with id=0. This layer stores the user blobs only and don't make any computations. In fact, this layer provides the only way to pass user data into the network. As any other layer, this layer can label its outputs and this function provides an easy way to do this.
Python prototype (for reference):
setInputsNames(inputBlobNames) -> None
@spec setParam(t(), binary(), integer(), Evision.Mat.maybe_mat_in()) :: :ok | {:error, String.t()}
@spec setParam(t(), integer(), integer(), Evision.Mat.maybe_mat_in()) :: :ok | {:error, String.t()}
Variant 1:
Positional Arguments
- layerName:
String
- numParam:
int
- blob:
Evision.Mat
Python prototype (for reference):
setParam(layerName, numParam, blob) -> None
Variant 2:
Sets the new value for the learned param of the layer.
Positional Arguments
layer:
int
.name or id of the layer.
numParam:
int
.index of the layer parameter in the Layer::blobs array.
blob:
Evision.Mat
.the new value.
@see Layer::blobs Note: If shape of the new blob differs from the previous shape, then the following forward pass may fail.
Python prototype (for reference):
setParam(layer, numParam, blob) -> None
Ask network to use specific computation backend where it supported.
Positional Arguments
backendId:
int
.backend identifier.
@see Backend If OpenCV is compiled with Intel's Inference Engine library, DNN_BACKEND_DEFAULT means DNN_BACKEND_INFERENCE_ENGINE. Otherwise it equals to DNN_BACKEND_OPENCV.
Python prototype (for reference):
setPreferableBackend(backendId) -> None
Ask network to make computations on specific target device.
Positional Arguments
targetId:
int
.target identifier.
@see Target List of supported combinations backend / target: | | DNN_BACKEND_OPENCV | DNN_BACKEND_INFERENCE_ENGINE | DNN_BACKEND_HALIDE | DNN_BACKEND_CUDA | |------------------------|--------------------|------------------------------|--------------------|-------------------| | DNN_TARGET_CPU | + | + | + | | | DNN_TARGET_OPENCL | + | + | + | | | DNN_TARGET_OPENCL_FP16 | + | + | | | | DNN_TARGET_MYRIAD | | + | | | | DNN_TARGET_FPGA | | + | | | | DNN_TARGET_CUDA | | | | + | | DNN_TARGET_CUDA_FP16 | | | | + | | DNN_TARGET_HDDL | | + | | |
Python prototype (for reference):
setPreferableTarget(targetId) -> None