[−][src]Trait opencv::dnn::LayerTrait
This interface class allows to build new Layers - are building blocks of networks.
Each class, derived from Layer, must implement allocate() methods to declare own outputs and forward() to compute outputs. Also before using the new layer into networks you must register your layer by using one of @ref dnnLayerFactory "LayerFactory" macros.
Required methods
pub fn as_raw_Layer(&self) -> *const c_void
[src]
pub fn as_raw_mut_Layer(&mut self) -> *mut c_void
[src]
Provided methods
pub fn blobs(&mut self) -> Vector<Mat>
[src]
List of learned parameters must be stored here to allow read them by using Net::getParam().
pub fn set_blobs(&mut self, val: Vector<Mat>)
[src]
List of learned parameters must be stored here to allow read them by using Net::getParam().
pub fn name(&self) -> String
[src]
Name of the layer instance, can be used for logging or other internal purposes.
pub fn set_name(&mut self, val: &str)
[src]
Name of the layer instance, can be used for logging or other internal purposes.
pub fn typ(&self) -> String
[src]
Type name which was used for creating layer by layer factory.
pub fn set_type(&mut self, val: &str)
[src]
Type name which was used for creating layer by layer factory.
pub fn preferable_target(&self) -> i32
[src]
prefer target for layer forwarding
pub fn set_preferable_target(&mut self, val: i32)
[src]
prefer target for layer forwarding
pub fn finalize(
&mut self,
inputs: &dyn ToInputArray,
outputs: &mut dyn ToOutputArray
) -> Result<()>
[src]
&mut self,
inputs: &dyn ToInputArray,
outputs: &mut dyn ToOutputArray
) -> Result<()>
Computes and sets internal parameters according to inputs, outputs and blobs.
Parameters
- inputs: vector of already allocated input blobs
- outputs:[out] vector of already allocated output blobs
If this method is called after network has allocated all memory for input and output blobs and before inferencing.
pub fn forward_mat(
&mut self,
input: &mut Vector<Mat>,
output: &mut Vector<Mat>,
internals: &mut Vector<Mat>
) -> Result<()>
[src]
&mut self,
input: &mut Vector<Mat>,
output: &mut Vector<Mat>,
internals: &mut Vector<Mat>
) -> Result<()>
Use Layer::forward(InputArrayOfArrays, OutputArrayOfArrays, OutputArrayOfArrays) instead
Given the @p input blobs, computes the output @p blobs.
Deprecated: Use Layer::forward(InputArrayOfArrays, OutputArrayOfArrays, OutputArrayOfArrays) instead
Parameters
- input: the input blobs.
- output:[out] allocated output blobs, which will store results of the computation.
- internals:[out] allocated internal blobs
pub fn forward(
&mut self,
inputs: &dyn ToInputArray,
outputs: &mut dyn ToOutputArray,
internals: &mut dyn ToOutputArray
) -> Result<()>
[src]
&mut self,
inputs: &dyn ToInputArray,
outputs: &mut dyn ToOutputArray,
internals: &mut dyn ToOutputArray
) -> Result<()>
Given the @p input blobs, computes the output @p blobs.
Parameters
- inputs: the input blobs.
- outputs:[out] allocated output blobs, which will store results of the computation.
- internals:[out] allocated internal blobs
pub fn forward_fallback(
&mut self,
inputs: &dyn ToInputArray,
outputs: &mut dyn ToOutputArray,
internals: &mut dyn ToOutputArray
) -> Result<()>
[src]
&mut self,
inputs: &dyn ToInputArray,
outputs: &mut dyn ToOutputArray,
internals: &mut dyn ToOutputArray
) -> Result<()>
Given the @p input blobs, computes the output @p blobs.
Parameters
- inputs: the input blobs.
- outputs:[out] allocated output blobs, which will store results of the computation.
- internals:[out] allocated internal blobs
pub fn finalize_mat_to(
&mut self,
inputs: &Vector<Mat>,
outputs: &mut Vector<Mat>
) -> Result<()>
[src]
&mut self,
inputs: &Vector<Mat>,
outputs: &mut Vector<Mat>
) -> Result<()>
Use Layer::finalize(InputArrayOfArrays, OutputArrayOfArrays) instead
@brief Computes and sets internal parameters according to inputs, outputs and blobs.
Parameters
- inputs: vector of already allocated input blobs
- outputs:[out] vector of already allocated output blobs
If this method is called after network has allocated all memory for input and output blobs and before inferencing.
Overloaded parameters
Deprecated: Use Layer::finalize(InputArrayOfArrays, OutputArrayOfArrays) instead
pub fn finalize_mat(&mut self, inputs: &Vector<Mat>) -> Result<Vector<Mat>>
[src]
Use Layer::finalize(InputArrayOfArrays, OutputArrayOfArrays) instead
@brief Computes and sets internal parameters according to inputs, outputs and blobs.
Parameters
- inputs: vector of already allocated input blobs
- outputs:[out] vector of already allocated output blobs
If this method is called after network has allocated all memory for input and output blobs and before inferencing.
Overloaded parameters
Deprecated: Use Layer::finalize(InputArrayOfArrays, OutputArrayOfArrays) instead
pub fn run(
&mut self,
inputs: &Vector<Mat>,
outputs: &mut Vector<Mat>,
internals: &mut Vector<Mat>
) -> Result<()>
[src]
&mut self,
inputs: &Vector<Mat>,
outputs: &mut Vector<Mat>,
internals: &mut Vector<Mat>
) -> Result<()>
This method will be removed in the future release.
Allocates layer and computes output.
Deprecated: This method will be removed in the future release.
pub fn input_name_to_index(&mut self, input_name: &str) -> Result<i32>
[src]
Returns index of input blob into the input array.
Parameters
- inputName: label of input blob
Each layer input and output can be labeled to easily identify them using "%<layer_name%>[.output_name]" notation. This method maps label of input blob to its index into input vector.
pub fn output_name_to_index(&mut self, output_name: &str) -> Result<i32>
[src]
pub fn support_backend(&mut self, backend_id: i32) -> Result<bool>
[src]
Ask layer if it support specific backend for doing computations.
Parameters
- backendId: computation backend identifier.
See also
Backend
pub fn init_halide(
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
[src]
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
Returns Halide backend node.
Parameters
- inputs: Input Halide buffers.
See also
BackendNode, BackendWrapper
Input buffers should be exactly the same that will be used in forward invocations. Despite we can use Halide::ImageParam based on input shape only, it helps prevent some memory management issues (if something wrong, Halide tests will be failed).
pub fn init_inf_engine(
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
[src]
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
pub fn init_ngraph(
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>,
nodes: &Vector<Ptr<BackendNode>>
) -> Result<Ptr<BackendNode>>
[src]
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>,
nodes: &Vector<Ptr<BackendNode>>
) -> Result<Ptr<BackendNode>>
pub fn init_vk_com(
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
[src]
&mut self,
inputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
pub fn init_cuda(
&mut self,
context: *mut c_void,
inputs: &Vector<Ptr<dyn BackendWrapper>>,
outputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
[src]
&mut self,
context: *mut c_void,
inputs: &Vector<Ptr<dyn BackendWrapper>>,
outputs: &Vector<Ptr<dyn BackendWrapper>>
) -> Result<Ptr<BackendNode>>
Returns a CUDA backend node
Parameters
- context: void pointer to CSLContext object
- inputs: layer inputs
- outputs: layer outputs
pub fn apply_halide_scheduler(
&self,
node: &mut Ptr<BackendNode>,
inputs: &Vector<Mat>,
outputs: &Vector<Mat>,
target_id: i32
) -> Result<()>
[src]
&self,
node: &mut Ptr<BackendNode>,
inputs: &Vector<Mat>,
outputs: &Vector<Mat>,
target_id: i32
) -> Result<()>
Automatic Halide scheduling based on layer hyper-parameters.
Parameters
- node: Backend node with Halide functions.
- inputs: Blobs that will be used in forward invocations.
- outputs: Blobs that will be used in forward invocations.
- targetId: Target identifier
See also
BackendNode, Target
Layer don't use own Halide::Func members because we can have applied layers fusing. In this way the fused function should be scheduled.
pub fn try_attach(
&mut self,
node: &Ptr<BackendNode>
) -> Result<Ptr<BackendNode>>
[src]
&mut self,
node: &Ptr<BackendNode>
) -> Result<Ptr<BackendNode>>
Implement layers fusing.
Parameters
- node: Backend node of bottom layer.
See also
BackendNode
Actual for graph-based backends. If layer attached successfully, returns non-empty cv::Ptr to node of the same backend. Fuse only over the last function.
pub fn set_activation(
&mut self,
layer: &Ptr<dyn ActivationLayer>
) -> Result<bool>
[src]
&mut self,
layer: &Ptr<dyn ActivationLayer>
) -> Result<bool>
Tries to attach to the layer the subsequent activation layer, i.e. do the layer fusion in a partial case.
Parameters
- layer: The subsequent activation layer.
Returns true if the activation layer has been attached successfully.
pub fn try_fuse(&mut self, top: &mut Ptr<Layer>) -> Result<bool>
[src]
Try to fuse current layer with a next one
Parameters
- top: Next layer to be fused.
Returns
True if fusion was performed.
pub fn get_scale_shift(&self, scale: &mut Mat, shift: &mut Mat) -> Result<()>
[src]
Returns parameters of layers with channel-wise multiplication and addition.
Parameters
- scale:[out] Channel-wise multipliers. Total number of values should be equal to number of channels.
- shift:[out] Channel-wise offsets. Total number of values should be equal to number of channels.
Some layers can fuse their transformations with further layers. In example, convolution + batch normalization. This way base layer use weights from layer after it. Fused layer is skipped. By default, @p scale and @p shift are empty that means layer has no element-wise multiplications or additions.
pub fn unset_attached(&mut self) -> Result<()>
[src]
"Deattaches" all the layers, attached to particular layer.
pub fn get_memory_shapes(
&self,
inputs: &Vector<MatShape>,
required_outputs: i32,
outputs: &mut Vector<MatShape>,
internals: &mut Vector<MatShape>
) -> Result<bool>
[src]
&self,
inputs: &Vector<MatShape>,
required_outputs: i32,
outputs: &mut Vector<MatShape>,
internals: &mut Vector<MatShape>
) -> Result<bool>
pub fn get_flops(
&self,
inputs: &Vector<MatShape>,
outputs: &Vector<MatShape>
) -> Result<i64>
[src]
&self,
inputs: &Vector<MatShape>,
outputs: &Vector<MatShape>
) -> Result<i64>
pub fn update_memory_shapes(
&mut self,
inputs: &Vector<MatShape>
) -> Result<bool>
[src]
&mut self,
inputs: &Vector<MatShape>
) -> Result<bool>