prepare_deep_counting_model🔗
Short description🔗
prepare_deep_counting_model — Set templates of a Deep Counting model.
Signature🔗
prepare_deep_counting_model( image Templates, deep_counting DeepCountingHandle )
Description🔗
prepare_deep_counting_model sets the templates of the objects that
should be counted by the Deep Counting model DeepCountingHandle.
When applying the Deep Counting model using apply_deep_counting_model,
objects in the search images that are similar to the provided templates
are detected and counted.
Note that this operator overwrites any previously set templates.
To also count scaled and rotated variants of the provided templates,
an automatic augmentation of the templates can be enabled by setting
the parameters 'angle_start', 'angle_end',
'angle_step', 'scale_min', 'scale_max', and
'scale_step' using create_deep_counting_model or
set_deep_counting_model_param before calling
apply_deep_counting_model.
When changing parameters of the Deep Counting model that influence the
template creation, prepare_deep_counting_model must be re-run
before apply_deep_counting_model.
The list of such parameters is provided in get_deep_counting_model_param.
Attention🔗
System requirements:
To run this operator on GPU (see get_deep_counting_model_param),
cuDNN and cuBLAS are required.
For further details, please refer to the “Installation Guide”,
paragraph “Requirements for Deep Learning and Deep-Learning-Based Methods”.
Alternatively, this operator can also be run on CPU.
Execution information🔗
Execution information
-
Multithreading type: reentrant (runs in parallel with non-exclusive operators).
-
Multithreading scope: global (may be called from any thread).
-
Automatically parallelized on internal data level.
This operator modifies the state of the following input parameter:
During execution of this operator, access to the value of this parameter must be synchronized if it is used across multiple threads.
Parameters🔗
Templates (input_object) (multichannel-)image(-array) → object (byte / real)
Template image(s) with regions.
DeepCountingHandle (input_control, state is modified) deep_counting → (handle)
Handle of the Deep Counting model.
Result🔗
If the handle of the model is valid, the operator
prepare_deep_counting_model returns the value 2 (H_MSG_TRUE). If necessary
an exception is raised.
Combinations with other operators🔗
Combinations
Possible predecessors
create_deep_counting_model, set_deep_counting_model_param, get_deep_counting_model_param, read_deep_counting_model
Possible successors
Alternatives
See also
Module🔗
Matching