def test_simple_pursuit_curriculum_all_variables(language_generator):
curriculum_test(
make_simple_pursuit_curriculum(
num_instances=15,
num_objects_in_instance=4,
num_noise_instances=2,
language_generator=language_generator,
))
def build_pursuit_curriculum(
num_samples: Optional[int],
num_noise_objects: Optional[int],
language_generator: LanguageGenerator[
HighLevelSemanticsSituation, LinearizedDependencyTree
],
*,
pursuit_curriculum_params: Parameters = Parameters.empty(),
) -> Sequence[Phase1InstanceGroup]:
num_instances = pursuit_curriculum_params.integer(
"num_instances", default=num_samples if num_samples else 10
)
num_noise_instances = pursuit_curriculum_params.integer(
"num_noise_instances", default=num_noise_objects if num_noise_objects else 2
)
num_objects_in_instance = pursuit_curriculum_params.integer(
"num_objects_in_instance", default=3
)
add_gaze = pursuit_curriculum_params.boolean("add_gaze", default=False)
prob_given = pursuit_curriculum_params.floating_point("prob_given", default=1.0)
prob_not_given = pursuit_curriculum_params.floating_point(
"prob_not_given", default=0.0
)
rng = random.Random()
rng.seed(0)
gaze_perciever = GazePerceivedNoisily(
rng=rng,
prob_gaze_perceived_given_gaze=prob_given,
prob_gaze_perceived_given_not_gaze=prob_not_given,
)
perception_generator = HighLevelSemanticsSituationToDevelopmentalPrimitivePerceptionGenerator(
ontology=GAILA_PHASE_2_ONTOLOGY, gaze_strategy=gaze_perciever
)
return [
make_simple_pursuit_curriculum(
target_objects=M6_CURRICULUM_ALL_OBJECTS,
num_instances=num_instances,
num_objects_in_instance=num_objects_in_instance,
num_noise_instances=num_noise_instances,
language_generator=language_generator,
add_gaze=add_gaze,
perception_generator=perception_generator,
)
]
def test_pursuit_object_learner_with_gaze(language_mode):
target_objects = [
BALL,
# PERSON,
# CHAIR,
# TABLE,
DOG,
# BIRD,
BOX,
]
language_generator = phase1_language_generator(language_mode)
target_test_templates = []
for obj in target_objects:
# Create train and test templates for the target objects
test_obj_object = object_variable("obj-with-color", obj)
test_template = Phase1SituationTemplate(
"colored-obj-object",
salient_object_variables=[test_obj_object],
syntax_hints=[IGNORE_COLORS],
gazed_objects=[test_obj_object],
)
target_test_templates.extend(
all_possible(
test_template,
chooser=PHASE1_CHOOSER_FACTORY(),
ontology=GAILA_PHASE_1_ONTOLOGY,
))
rng = random.Random()
rng.seed(0)
# We can use this to generate the actual pursuit curriculum
train_curriculum = make_simple_pursuit_curriculum(
target_objects=target_objects,
num_instances=30,
num_objects_in_instance=3,
num_noise_instances=0,
language_generator=language_generator,
add_gaze=True,
)
test_obj_curriculum = phase1_instances(
"obj test",
situations=target_test_templates,
language_generator=language_generator,
)
# All parameters should be in the range 0-1.
# Learning factor works better when kept < 0.5
# Graph matching threshold doesn't seem to matter that much, as often seems to be either a
# complete or a very small match.
# The lexicon threshold works better between 0.07-0.3, but we need to play around with it because we end up not
# lexicalize items sufficiently because of diminishing lexicon probability through training
rng = random.Random()
rng.seed(0)
learner = IntegratedTemplateLearner(object_learner=PursuitObjectLearnerNew(
learning_factor=0.05,
graph_match_confirmation_threshold=0.7,
lexicon_entry_threshold=0.7,
rng=rng,
smoothing_parameter=0.002,
ontology=GAILA_PHASE_1_ONTOLOGY,
language_mode=language_mode,
rank_gaze_higher=True,
))
for training_stage in [train_curriculum]:
for (
_,
linguistic_description,
perceptual_representation,
) in training_stage.instances():
learner.observe(
LearningExample(perceptual_representation,
linguistic_description))
for test_instance_group in [test_obj_curriculum]:
for (
_,
test_instance_language,
test_instance_perception,
) in test_instance_group.instances():
logging.info("lang: %s", test_instance_language)
descriptions_from_learner = learner.describe(
test_instance_perception)
gold = test_instance_language.as_token_sequence()
assert gold in [
desc.as_token_sequence() for desc in descriptions_from_learner
]
def test_simple_pursuit_curriculum_with_noise(language_generator):
curriculum_test(make_simple_pursuit_curriculum(None, 2,
language_generator))
def test_simple_pursuit_curriculum(language_generator):
curriculum_test(
make_simple_pursuit_curriculum(None, None, language_generator))