def create_dataset(project_id, display_name):
"""Create a dataset."""
# [START automl_vision_object_detection_create_dataset]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# display_name = "your_datasets_display_name"
client = automl.AutoMlClient()
# A resource that represents Google Cloud Platform location.
project_location = f"projects/{project_id}/locations/us-central1"
metadata = automl.ImageObjectDetectionDatasetMetadata()
dataset = automl.Dataset(
display_name=display_name,
image_object_detection_dataset_metadata=metadata,
)
# Create a dataset with the dataset metadata in the region.
response = client.create_dataset(parent=project_location, dataset=dataset)
created_dataset = response.result()
# Display the dataset information
print("Dataset name: {}".format(created_dataset.name))
print("Dataset id: {}".format(created_dataset.name.split("/")[-1]))
def create_dataset(project_id, display_name):
"""Create a dataset."""
# [START automl_language_text_classification_create_dataset]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# display_name = "YOUR_DATASET_NAME"
client = automl.AutoMlClient()
# A resource that represents Google Cloud Platform location.
project_location = f"projects/{project_id}/locations/us-central1"
# Specify the classification type
# Types:
# MultiLabel: Multiple labels are allowed for one example.
# MultiClass: At most one label is allowed per example.
metadata = automl.TextClassificationDatasetMetadata(
classification_type=automl.ClassificationType.MULTICLASS)
dataset = automl.Dataset(
display_name=display_name,
text_classification_dataset_metadata=metadata,
)
# Create a dataset with the dataset metadata in the region.
response = client.create_dataset(parent=project_location, dataset=dataset)
created_dataset = response.result()
# Display the dataset information
print("Dataset name: {}".format(created_dataset.name))
print("Dataset id: {}".format(created_dataset.name.split("/")[-1]))
def create_dataset(project_id, display_name):
"""Create a dataset."""
# [START automl_translate_create_dataset]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# display_name = "YOUR_DATASET_NAME"
client = automl.AutoMlClient()
# A resource that represents Google Cloud Platform location.
project_location = f"projects/{project_id}/locations/us-central1"
# For a list of supported languages, see:
# https://cloud.google.com/translate/automl/docs/languages
dataset_metadata = automl.TranslationDatasetMetadata(
source_language_code="en", target_language_code="ja")
dataset = automl.Dataset(
display_name=display_name,
translation_dataset_metadata=dataset_metadata,
)
# Create a dataset with the dataset metadata in the region.
response = client.create_dataset(parent=project_location, dataset=dataset)
created_dataset = response.result()
# Display the dataset information
print("Dataset name: {}".format(created_dataset.name))
print("Dataset id: {}".format(created_dataset.name.split("/")[-1]))
def create_dataset(project_id, display_name):
"""Create a dataset."""
# [START automl_language_sentiment_analysis_create_dataset]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# display_name = "YOUR_DATASET_NAME"
client = automl.AutoMlClient()
# A resource that represents Google Cloud Platform location.
project_location = f"projects/{project_id}/locations/us-central1"
# Each dataset requires a sentiment score with a defined sentiment_max
# value, for more information on TextSentimentDatasetMetadata, see:
# https://cloud.google.com/natural-language/automl/docs/prepare#sentiment-analysis
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsentimentdatasetmetadata
metadata = automl.TextSentimentDatasetMetadata(
sentiment_max=4) # Possible max sentiment score: 1-10
dataset = automl.Dataset(display_name=display_name,
text_sentiment_dataset_metadata=metadata)
# Create a dataset with the dataset metadata in the region.
response = client.create_dataset(parent=project_location, dataset=dataset)
created_dataset = response.result()
# Display the dataset information
print("Dataset name: {}".format(created_dataset.name))
print("Dataset id: {}".format(created_dataset.name.split("/")[-1]))
def train_text_extraction_model(
self,
display_name: (str, 'the display name for the dataset and model'),
input_paths:
(str,
'the paths to csv files describing the input data for a new dataset'
) = '',
dataset_id: (str, 'the id of an existing dataset to reuse') = '',
train_budget_milli_node_hours: int = 24000) -> Operation:
dataset = None
if len(dataset_id) == 0:
dataset = automl.Dataset(
display_name=display_name,
text_extraction_dataset_metadata={},
)
metadata = automl.TextExtractionModelMetadata()
model = automl.Model(display_name=display_name,
dataset_id=dataset_id,
text_extraction_model_metadata=metadata)
long_running_operation = self.train_automl_model(
model=model,
dataset=dataset,
dataset_id=dataset_id,
input_paths=input_paths)
return long_running_operation
def dataset_id():
client = automl.AutoMlClient()
project_location = f"projects/{PROJECT_ID}/locations/us-central1"
display_name = "test_" + datetime.datetime.now().strftime("%Y%m%d%H%M%S")
metadata = automl.TextExtractionDatasetMetadata()
dataset = automl.Dataset(
display_name=display_name, text_extraction_dataset_metadata=metadata
)
response = client.create_dataset(parent=project_location, dataset=dataset)
dataset_id = response.result().name.split("/")[-1]
yield dataset_id
def train_image_classification_model(
self,
display_name: (str, 'the display name for the dataset and model'),
input_paths:
(str,
'the paths to csv files describing the input data for a new dataset'
) = '',
dataset_id: (str, 'the id of an existing dataset to reuse') = '',
classification_type: (automl.ClassificationType,
'MULTICLASS or MULTILABEL'
) = automl.ClassificationType.MULTICLASS,
train_budget_milli_node_hours: int = 24000) -> Operation:
dataset = None
if len(dataset_id) == 0:
# Specify the classification type
# Types:
# MultiLabel: Multiple labels are allowed for one example.
# MultiClass: At most one label is allowed per example.
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#classificationtype
metadata = automl.ImageClassificationDatasetMetadata(
classification_type=classification_type)
dataset = automl.Dataset(
display_name=display_name,
image_classification_dataset_metadata=metadata,
)
# Leave model unset to use the default base model provided by Google
# train_budget_milli_node_hours: The actual train_cost will be equal or
# less than this value.
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#imageclassificationmodelmetadata
metadata = automl.ImageClassificationModelMetadata(
train_budget_milli_node_hours=train_budget_milli_node_hours)
model = automl.Model(
display_name=display_name,
dataset_id=dataset_id,
image_classification_model_metadata=metadata,
)
long_running_operation = self.train_automl_model(
model=model,
dataset=dataset,
dataset_id=dataset_id,
input_paths=input_paths)
return long_running_operation
def train_text_classification_model(
self,
display_name: (str, 'the display name for the dataset and model'),
input_paths: (
str,
'the paths to csv files describing the input data for a new dataset'
) = '',
dataset_id: (str, 'the id of an existing dataset to reuse') = '',
classification_type: (
automl.ClassificationType,
'MULTICLASS or MULTILABEL') = automl.ClassificationType.MULTICLASS
) -> Operation:
dataset = None
if len(dataset_id) == 0:
# Specify the classification type
# Types:
# MultiLabel: Multiple labels are allowed for one example.
# MultiClass: At most one label is allowed per example.
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#classificationtype
metadata = automl.TextClassificationDatasetMetadata(
classification_type=classification_type)
dataset = automl.Dataset(
display_name=display_name,
text_classification_dataset_metadata=metadata,
)
model = automl.Model(display_name=display_name,
dataset_id=dataset_id,
text_classification_model_metadata={})
long_running_operation = self.train_automl_model(
model=model,
dataset=dataset,
dataset_id=dataset_id,
input_paths=input_paths)
return long_running_operation
display_name = "%s_%d_%d_%d"%(data_config['dataset_name'],
int(data_config['noise_ratio']*100),
data_config['pos_limit'], data_config['neg_limit'])
start_time = time.time()
client = automl.AutoMlClient()
project_location = f"projects/{project_id}/locations/us-central1"
metadata = automl.ImageClassificationDatasetMetadata(
classification_type=automl.ClassificationType.MULTICLASS
)
dataset = automl.Dataset(
display_name=display_name,
image_classification_dataset_metadata=metadata,
)
# Create a dataset with the dataset metadata in the region.
response = client.create_dataset(parent=project_location, dataset=dataset)
created_dataset = response.result()
# Display the dataset information
print("Dataset name: {}".format(created_dataset.name))
print("Dataset id: {}".format(created_dataset.name.split("/")[-1]))
storage_client = storage.Client()
bucket = storage_client.get_bucket(f"{project_id}-vcm")
pos_train_images_gc = add_images_to_gc(data['pos_train_images'])
