def automl_image_classification_training_job_sample(
project: str,
location: str,
dataset_id: str,
display_name: str,
):
aiplatform.init(project=project, location=location)
dataset = aiplatform.ImageDataset(dataset_id)
job = aiplatform.AutoMLImageTrainingJob(
display_name=display_name,
prediction_type="classification",
multi_label=False,
model_type="CLOUD",
base_model=None,
)
model = job.run(
dataset=dataset,
model_display_name=display_name,
training_fraction_split=0.6,
validation_fraction_split=0.2,
test_fraction_split=0.2,
budget_milli_node_hours=8000,
disable_early_stopping=False,
)
print(model.display_name)
print(model.name)
print(model.resource_name)
print(model.description)
print(model.uri)
return model
def test_get_nonexistent_dataset(self):
"""Ensure attempting to retrieve a dataset that doesn't exist raises
a Google API core 404 exception."""
aiplatform.init(project=_TEST_PROJECT, location=_TEST_LOCATION)
# AI Platform service returns 404
with pytest.raises(exceptions.NotFound):
aiplatform.ImageDataset(dataset_name="0")
def test_get_existing_dataset(self):
"""Retrieve a known existing dataset, ensure SDK successfully gets the
dataset resource."""
aiplatform.init(project=_TEST_PROJECT, location=_TEST_LOCATION)
flowers_dataset = aiplatform.ImageDataset(dataset_name=_TEST_IMAGE_DATASET_ID)
assert flowers_dataset.name == _TEST_IMAGE_DATASET_ID
assert flowers_dataset.display_name == _TEST_DATASET_DISPLAY_NAME
def create_training_pipeline_custom_package_job_sample(
project: str,
location: str,
staging_bucket: str,
display_name: str,
python_package_gcs_uri: str,
python_module_name: str,
container_uri: str,
model_serving_container_image_uri: str,
dataset_id: Optional[str] = None,
model_display_name: Optional[str] = None,
args: Optional[List[Union[str, float, int]]] = None,
replica_count: int = 1,
machine_type: str = "n1-standard-4",
accelerator_type: str = "ACCELERATOR_TYPE_UNSPECIFIED",
accelerator_count: int = 0,
training_fraction_split: float = 0.8,
validation_fraction_split: float = 0.1,
test_fraction_split: float = 0.1,
sync: bool = True,
):
aiplatform.init(project=project,
location=location,
staging_bucket=staging_bucket)
job = aiplatform.CustomPythonPackageTrainingJob(
display_name=display_name,
python_package_gcs_uri=python_package_gcs_uri,
python_module_name=python_module_name,
container_uri=container_uri,
model_serving_container_image_uri=model_serving_container_image_uri,
)
# This example uses an ImageDataset, but you can use another type
dataset = aiplatform.ImageDataset(dataset_id) if dataset_id else None
model = job.run(
dataset=dataset,
model_display_name=model_display_name,
args=args,
replica_count=replica_count,
machine_type=machine_type,
accelerator_type=accelerator_type,
accelerator_count=accelerator_count,
training_fraction_split=training_fraction_split,
validation_fraction_split=validation_fraction_split,
test_fraction_split=test_fraction_split,
sync=sync,
)
model.wait()
print(model.display_name)
print(model.resource_name)
print(model.uri)
return model
def create_training_pipeline_custom_training_managed_dataset_sample(
project: str,
location: str,
display_name: str,
script_path: str,
container_uri: str,
model_serving_container_image_uri: str,
dataset_id: int,
model_display_name: Optional[str] = None,
args: Optional[List[Union[str, float, int]]] = None,
replica_count: int = 0,
machine_type: str = "n1-standard-4",
accelerator_type: str = "ACCELERATOR_TYPE_UNSPECIFIED",
accelerator_count: int = 0,
training_fraction_split: float = 0.8,
validation_fraction_split: float = 0.1,
test_fraction_split: float = 0.1,
sync: bool = True,
):
aiplatform.init(project=project, location=location)
job = aiplatform.CustomTrainingJob(
display_name=display_name,
script_path=script_path,
container_uri=container_uri,
model_serving_container_image_uri=model_serving_container_image_uri,
)
my_image_ds = aiplatform.ImageDataset(dataset_id)
model = job.run(
dataset=my_image_ds,
model_display_name=model_display_name,
args=args,
replica_count=replica_count,
machine_type=machine_type,
accelerator_type=accelerator_type,
accelerator_count=accelerator_count,
training_fraction_split=training_fraction_split,
validation_fraction_split=validation_fraction_split,
test_fraction_split=test_fraction_split,
sync=sync,
)
model.wait()
print(model.display_name)
print(model.resource_name)
print(model.uri)
return model
def image_dataset_import_data_sample(
project: str, location: str, src_uris: list, import_schema_uri: str, dataset_id: str
):
aiplatform.init(project=project, location=location)
ds = aiplatform.ImageDataset(dataset_id)
ds = ds.import_data(
gcs_source=src_uris, import_schema_uri=import_schema_uri, sync=True
)
print(ds.display_name)
print(ds.name)
print(ds.resource_name)
return ds
def create_training_pipeline_image_classification_sample(
project: str,
display_name: str,
dataset_id: int,
location: str = "us-central1",
model_display_name: str = None,
training_fraction_split: float = 0.8,
validation_fraction_split: float = 0.1,
test_fraction_split: float = 0.1,
budget_milli_node_hours: int = 8000,
disable_early_stopping: bool = False,
sync: bool = True,
):
aiplatform.init(project=project, location=location)
job = aiplatform.AutoMLImageTrainingJob(display_name=display_name)
my_image_ds = aiplatform.ImageDataset(dataset_id)
model = job.run(
dataset=my_image_ds,
model_display_name=model_display_name,
training_fraction_split=training_fraction_split,
validation_fraction_split=validation_fraction_split,
test_fraction_split=test_fraction_split,
budget_milli_node_hours=budget_milli_node_hours,
disable_early_stopping=disable_early_stopping,
sync=sync,
)
model.wait()
print(model.display_name)
print(model.resource_name)
print(model.uri)
return model