mlair.run_modules.model_setup
¶
Model setup module.
Module Contents¶
Classes¶
Set up the model. |
Attributes¶
-
mlair.run_modules.model_setup.
__date__
= 2019-12-02¶
-
class
mlair.run_modules.model_setup.
ModelSetup
¶ Bases:
mlair.run_modules.run_environment.RunEnvironment
Set up the model.
- Schedule of model setup:
set channels (from variables dimension)
build imported model
plot model architecture
load weights if enabled (e.g. to resume a training)
set callbacks and checkpoint
compile model
- Required objects [scope] from data store:
experiment_path [.]
experiment_name [.]
train_model [.]
create_new_model [.]
generator [train]
model_class [.]
- Optional objects
lr_decay [model]
- Sets
channels [model]
model [model]
hist [model]
callbacks [model]
model_name [model]
all settings from model class like dropout_rate, initial_lr, and optimizer [model]
- Creates
plot of model architecture <model_name>.pdf
-
_run
(self)¶
-
_set_model_path
(self)¶
-
_set_shapes
(self)¶ Set input and output shapes from train collection.
-
_set_num_of_training_samples
(self)¶ Set number of training samples - needed for example for Bayesian NNs
-
compile_model
(self)¶ Compiles the keras model. Compile options are mandatory and have to be set by implementing set_compile() method in child class of AbstractModelClass.
-
_set_callbacks
(self)¶ Set all callbacks for the training phase.
Add all callbacks with the .add_callback statement. Finally, the advanced model checkpoint is added.
-
copy_model
(self)¶ Copy external model to internal experiment structure.
-
load_model
(self)¶ Try to load model from disk or skip if not possible.
-
build_model
(self)¶ Build model using input and output shapes from data store.
-
broadcast_custom_objects
(self)¶ Broadcast custom objects to keras utils.
This method is very important, because it adds the model’s custom objects to the keras utils. By doing so, all custom objects can be treated as standard keras modules. Therefore, problems related to model or callback loading are solved.
-
get_model_settings
(self)¶ Load all model settings and store in data store.
-
plot_model
(self)¶ Plot model architecture as <model_name>.pdf.
-
report_model
(self)¶