simulation.utils.machine_learning.models.test package

Submodules

simulation.utils.machine_learning.models.test.test_helper module

Functions:

test_get_norm_layer()	Check if get_norm_layer() returns a valid layer.
test_get_scheduler()	Check if get_scheduler() returns a scheduler.
test_init_weights()	Check if init_weights() runs without errors.
test_set_requires_grad()	Check if set_requires_grad() correctly changes requires_grad.
main()

test_get_norm_layer()

Check if get_norm_layer() returns a valid layer.

test_get_scheduler()

Check if get_scheduler() returns a scheduler.

test_init_weights()

Check if init_weights() runs without errors.

test_set_requires_grad()

Check if set_requires_grad() correctly changes requires_grad.

main()

simulation.utils.machine_learning.models.test.test_resnet_block module

Functions:

test_creating_resnet_block(norm_type, **kwargs)
main()

test_creating_resnet_block(norm_type, **kwargs)

main()

simulation.utils.machine_learning.models.test.test_resnet_generator module

Functions:

test_resnet_generator(norm_type, **kwargs)
main()

test_resnet_generator(norm_type, **kwargs)

main()

simulation.utils.machine_learning.models.test.test_wgan_critic module

Perform some basic tests for the WGAN critic.

Functions:

test_weight_clipping()
test_forward()
test_optimization_step()	Testing very basic functionality of optimizing.
main()

test_weight_clipping() → None

test_forward() → None

test_optimization_step()

Testing very basic functionality of optimizing.

Testing if the optimization works is hard. Here, some very basic things are tested:

• Does the wasserstein distance increase when running the optimization?

• Is the distance close to zero, if random distributions are given

  and the generator is the identity?

• Is the generator unchanged?

main()

Module contents