load_dl_model_weights — Load the weights of a source model into a target model.
load_dl_model_weights loads weights of a source model
DLModelHandleSource into a target model
Thereby applies for every layer in the target model: Its weights are only
changed if there is a layer in the source model having the same name and the
DLModelHandleSource must be different from
DLModelHandleTarget, i.e., you cannot use the same model handle as
source and target.
ChangesByLayer is a tuple indicating for every target layer how many
Its entries are sorted by ascending layer IDs. The layer IDs can be queried
via the operator
get_dl_model_param with the parameter
Note, that 'weights' means all weights and biases for all layers which can have such values (e.g., convolution, batchnorm, etc.).
load_dl_model_weights is only applicable to self-created
networks. For networks delivered by HALCON, the operator is not working.
Handle of the source deep learning model.
Handle of the target deep learning model.
Indicates for every target layer how many weights changed.
If the parameters are valid, the operator
returns the value TRUE. If necessary, an exception is raised.
Deep Learning Training