create_dl_layer_loss_focal🔗
Short description🔗
create_dl_layer_loss_focal — Create a focal loss layer.
Signature🔗
create_dl_layer_loss_focal( dl_layer DLLayerInput, dl_layer DLLayerTarget, dl_layer DLLayerWeights, dl_layer DLLayerNormalization, string LayerName, number LossWeight, number Gamma, number ClassWeights, string Type, attribute.name GenParamName, attribute.value GenParamValue, out dl_layer DLLayerLossFocal )
Description🔗
The operator create_dl_layer_loss_focal creates a focal loss layer
whose handle is returned in DLLayerLossFocal.
See the reference cited below for further
information about its definition and parameter meanings.
This layer expects multiple layers as input:
-
DLLayerInput: Specifies the prediction (e.g., a sigmoid or softmax layer). -
DLLayerTarget: Specifies the target sequences (originating from the ground truth information). -
DLLayerWeights: Specifies the weight sequences. This parameter is optional. If an empty tuple [] is passed for all values the weighting factor 1.0 is used. -
DLLayerNormalization: Specifies the factor to normalize the loss. This parameter is optional, it can be given by the layer handle as value or ignored handing over an empty tuple [].
The parameter LayerName sets an individual layer name.
Note that if creating a model using create_dl_model each layer of
the created network must have a unique name.
The parameter LossWeight is a overall loss weight if there are
multiple losses in the network.
The parameter Gamma is the exponent of the focal factor.
The parameter ClassWeights defines class specific weights. All
loss contributions of foreground samples of a class are weighted with
the given factor. The background samples are weighted by 1 - ClassWeights.
Typically, this is set to 1.0/(Number of samples of the class).
Note, the length of this array has to be either 1, then its broadcasted
to the number of classes, or it has to correspond to the number of classes.
The default value [] corresponds to a factor of 0.5 for
all classes.
Note, if the number of classes are changed on a network then the number of
class specific weights are also adapted and reset with the default value
0.5 for each class.
The parameter Type sets the focal loss options:
-
'focal_binary': Focal loss.
-
'sigmoid_focal_binary': Focal loss fused with sigmoid.
The following generic parameters GenParamName and the corresponding
values GenParamValue are supported:
-
'is_inference_output': Determines whether
apply_dl_modelwill include the output of this layer in the dictionaryDLResultBatcheven without specifying this layer inOutputs('true') or not ('false').Default: 'false'
Certain parameters of layers created using this operator
create_dl_layer_loss_focal can be set and retrieved using
further operators.
The following tables give an overview, which parameters can be set
using set_dl_model_layer_param and which ones can be retrieved
using get_dl_model_layer_param or get_dl_layer_param.
Note, the operators set_dl_model_layer_param and
get_dl_model_layer_param require a model created by
create_dl_model.
| Layer Parameters | set |
get |
|---|---|---|
'focal_type' (Type) |
x |
|
'gamma' (Gamma) |
x |
x |
'input_layer' (DLLayerInput, DLLayerTarget, DLLayerWeights, and/or DLLayerNormalization) |
x |
|
'loss_weight' (LossWeight) |
x |
x |
'name' (LayerName) |
x |
x |
'output_layer' (DLLayerLossFocal) |
x |
|
| 'shape' | x |
|
| 'type' | x |
| Generic Layer Parameters | set |
get |
|---|---|---|
| 'is_inference_output' | x |
x |
| 'num_trainable_params' | x |
Execution information🔗
Execution information
-
Multithreading type: reentrant (runs in parallel with non-exclusive operators).
-
Multithreading scope: global (may be called from any thread).
-
Processed without parallelization.
Parameters🔗
DLLayerInput (input_control) dl_layer → (handle)
Input layer.
DLLayerTarget (input_control) dl_layer → (handle)
Target layer.
DLLayerWeights (input_control) dl_layer → (handle)
Weights layer.
DLLayerNormalization (input_control) dl_layer → (handle)
Normalization layer.
Default: []
LayerName (input_control) string → (string)
Name of the output layer.
LossWeight (input_control) number → (real / integer)
Overall loss weight if there are multiple losses in the network.
Default: 1.0
Gamma (input_control) number → (real / integer)
Exponent of the focal factor.
Default: 2.0
ClassWeights (input_control) number(-array) → (real / integer)
Class specific weight.
Default: []
Type (input_control) string → (string)
Focal loss type.
Default: 'focal_binary'
List of values: 'focal_binary', 'sigmoid_focal_binary'
GenParamName (input_control) attribute.name(-array) → (string)
Generic input parameter names.
Default: []
List of values: 'is_inference_output'
GenParamValue (input_control) attribute.value(-array) → (string)
Generic input parameter values.
Default: []
Suggested values: 'true', 'false'
DLLayerLossFocal (output_control) dl_layer → (handle)
Focal loss layer.
References🔗
T. Lin, P. Goyal, R. Girshick, K. He and P. Dollar, “Focal Loss for Dense Object Detection,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 318-327, 1 Feb. 2020, doi: 10.1109/TPAMI.2018.2858826.
Module🔗
Deep Learning Professional