create_dl_layer_input🔗
Short description🔗
create_dl_layer_input — Create an input layer.
Signature🔗
create_dl_layer_input( string LayerName, number Shape, attribute.name GenParamName, attribute.value GenParamValue, out dl_layer DLLayerInput )
Description🔗
The operator create_dl_layer_input creates an input layer with
spatial dimensions given by Shape whose handle is returned in
DLLayerInput.
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.
When the created model is applied using e.g., apply_dl_model or
train_dl_model_batch, it must be possible to map an input with its
corresponding input layer.
Operators applying a model expect a feeding dictionary DLSample,
see Deep Learning / Model.
The mentioned mapping is done using dictionary entries, where the key
matches the input layer name. Thus, for an input of this layer a sample
dictionary will need an entry with the key LayerName (except if the
'input_type' is set to 'constant', see below).
The parameter Shape defines the shape of the input values (the
values given in the feeding dictionary DLSample) and
must be a tuple of length three, containing width,
height, and depth of the input. The tuple values must be
given as integer values and have have different meaning
depending on the input type:
-
for an input image the layer
Shapedefines the image size. Images shall be given with typereal(for information on image types see Image). -
for an input tuple its length will need to match the product of the individual values in
Shape, i.e.,width\(\times\)height\(\times\)depth.Tuple values are distributed along the column- (
width), row- (height), anddepth-axes in this order. Input tuple values can be given either asintegerorreal.
The batch size has to be set later with
set_dl_model_param, once the model has been created by
create_dl_model.
The following generic parameters GenParamName and the corresponding
values GenParamValue are supported:
-
'allow_smaller_tuple': For tuple inputs, setting 'allow_smaller_tuple' to 'true' allows to have an input tuple with less values than the total dimension given by
Shape. E.g., this can be the case if an input corresponds to the number of objects within one image and the number of objects changes from image to image. If fewer than the maximum number of values given by the total dimension ofShapeare present, the remaining values are set to zero.Shapeshould be set such that it fits the maximum expected length. For the example above this would be the maximum number of objects within one image present in the whole dataset.Default: 'false'.
-
'const_val': Constant output value.
Restriction: Only an integer or float is settable. This value is only settable or gettable if 'input_type' is set to 'constant'.
Default: 0.0.
-
'input_type': Defines the type of input that is expected. The following values are possible:
-
'default': The layer expects a number of input images corresponding to the batch size.
-
'region_to_bin': The layer expects a tuple of regions as input and internally converts it to a binary image where each region is encoded in one depth channel. Regions reaching out of the given dimensions are clipped to the width and height given by
Shape. The maximum number of regions is defined by the depth ofShape. If fewer than the maximum number of regions are given, the output is filled up with empty (zero) images. For example, this can be the case if the regions are corresponding to objects within an image and the number of objects changes from image to image. -
'constant': The layer does not expect any key value pair in the input dictionary. Instead all entries within the output of this layer are filled with the value given by 'const_val'.
Default: 'default'.
-
-
'keep_batch_size_const': For constant inputs, this parameter can be set to 'true', if the input should always keep its batch size constant, independent from changing the model batch size.
Default: 'false'.
-
'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 create_dl_layer_input
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 |
|---|---|---|
| 'input_layer' | x |
|
'name' (LayerName) |
x |
x |
'output_layer' (DLLayerInput) |
x |
|
'shape' (Shape) |
x |
|
| 'type' | x |
| Generic Layer Parameters | set |
get |
|---|---|---|
| 'allow_smaller_tuple' | x |
|
| 'const_val' | (x) |
(x) |
| 'input_type' | x |
|
| 'keep_batch_size_const' | x |
x |
| '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.
This operator returns a handle. Note that the state of an instance of this handle type may be changed by specific operators even though the handle is used as an input parameter by those operators.
Parameters🔗
LayerName (input_control) string → (string)
Name of the output layer.
Shape (input_control) number-array → (integer)
Dimensions of the input (width, height, depth).
Default: [224, 224, 3]
GenParamName (input_control) attribute.name(-array) → (string)
Generic input parameter names.
Default: []
List of values: 'allow_smaller_tuple', 'const_val', 'input_type', 'is_inference_output', 'keep_batch_size_const'
GenParamValue (input_control) attribute.value(-array) → (string / integer / real)
Generic input parameter values.
Default: []
Suggested values: 0.0, 'constant', 'default', 'false', 'region_to_bin', 'true'
DLLayerInput (output_control) dl_layer → (handle)
Input layer.
Example🔗
(HDevelop)
* Create a model for summation.
create_dl_layer_input ('input_a', [2, 3, 4], [], [], DLLayerInputA)
create_dl_layer_input ('input_b', [2, 3, 4], [], [], DLLayerInputB)
create_dl_layer_elementwise ([DLLayerInputA, DLLayerInputB], 'sum', \
'sum', [], [], [], DLLayerElementWise)
create_dl_model (DLLayerElementWise, DLModel)
set_dl_model_param (DLModel, 'runtime', 'cpu')
*
* Add 'input_a' as an inference model output.
set_dl_model_layer_param (DLModel, 'input_a', 'is_inference_output', 'true')
*
* Feed input data as tuple (a) or image (b).
create_dict (Sample)
set_dict_tuple (Sample, 'input_a', [1:(2*3*4)])
gen_empty_obj (InputB)
for I := 1 to 4 by 1
gen_image_const (Channel, 'real', 2, 3)
get_region_points (Channel, Rows, Cols)
set_grayval (Channel, Rows, Cols, gen_tuple_const(|Rows|, I))
append_channel (InputB, Channel, InputB)
endfor
set_dict_object (InputB, Sample, 'input_b')
*
* Apply the model for summation and get results.
set_dl_model_param (DLModel, 'batch_size', 2)
apply_dl_model (DLModel, [Sample,Sample], [], Result)
get_dict_object (Sum, Result[0], 'sum')
get_dict_object (TupleInputA, Result[1], 'input_a')
Combinations with other operators🔗
Combinations
Possible successors
create_dl_layer_activation, create_dl_layer_batch_normalization, create_dl_layer_class_id_conversion, create_dl_layer_class_id_conversion, create_dl_layer_concat, create_dl_layer_convolution, create_dl_layer_dense, create_dl_layer_depth_max, create_dl_layer_dropout, create_dl_layer_elementwise, create_dl_layer_loss_cross_entropy, create_dl_layer_loss_ctc, create_dl_layer_loss_distance, create_dl_layer_loss_focal, create_dl_layer_loss_huber, create_dl_layer_lrn, create_dl_layer_pooling, create_dl_layer_reduce, create_dl_layer_reshape, create_dl_layer_softmax, create_dl_layer_transposed_convolution, create_dl_layer_zoom_factor, create_dl_layer_zoom_size, create_dl_layer_zoom_to_layer_size
Module🔗
Deep Learning Professional