def batch_predict(project_id, model_id, input_uri, output_uri):
"""Batch predict"""
# [START automl_batch_predict]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# input_uri = "gs://YOUR_BUCKET_ID/path/to/your/input/csv_or_jsonl"
# output_uri = "gs://YOUR_BUCKET_ID/path/to/save/results/"
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = f"projects/{project_id}/locations/us-central1/models/{model_id}"
gcs_source = automl.GcsSource(input_uris=[input_uri])
input_config = automl.BatchPredictInputConfig(gcs_source=gcs_source)
gcs_destination = automl.GcsDestination(output_uri_prefix=output_uri)
output_config = automl.BatchPredictOutputConfig(
gcs_destination=gcs_destination)
response = prediction_client.batch_predict(name=model_full_id,
input_config=input_config,
output_config=output_config)
print("Waiting for operation to complete...")
print(
f"Batch Prediction results saved to Cloud Storage bucket. {response.result()}"
)
def import_dataset(project_id, dataset_id, path):
"""Import a dataset."""
# [START automl_import_data]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# dataset_id = "YOUR_DATASET_ID"
# path = "gs://YOUR_BUCKET_ID/path/to/data.csv"
client = automl.AutoMlClient()
# Get the full path of the dataset.
dataset_full_id = client.dataset_path(project_id, "us-central1",
dataset_id)
# Get the multiple Google Cloud Storage URIs
input_uris = path.split(",")
gcs_source = automl.GcsSource(input_uris=input_uris)
input_config = automl.InputConfig(gcs_source=gcs_source)
# Import data from the input URI
response = client.import_data(name=dataset_full_id,
input_config=input_config)
print("Processing import...")
print("Data imported. {}".format(response.result()))
pos_train_images_gc = add_images_to_gc(data['pos_train_images'])
neg_train_images_gc = add_images_to_gc(data['neg_train_images'])
labels_csv = ''
labels_csv += '\n'.join(['%s,positive'%item for item in pos_train_images_gc])
labels_csv += '\n'.join(['%s,negative'%item for item in neg_train_images_gc])
blob = bucket.blob(f'csv/{display_name}.csv')
blob.upload_from_string(labels_csv)
csv_path = blob.public_url.replace('https://storage.googleapis.com/', 'gs://')
dataset_id = created_dataset.name.split("/")[-1]
dataset_full_id = client.dataset_path(project_id, "us-central1", dataset_id)
gcs_source = automl.GcsSource(input_uris=[csv_path])
input_config = automl.InputConfig(gcs_source=gcs_source)
# Import data from the input URI
response = client.import_data(name=dataset_full_id, input_config=input_config)
print("Processing import...")
print("Data imported. {}".format(response.result()))
start_training_time = time.time()
project_location = f"projects/{project_id}/locations/us-central1"
# 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
from google.cloud import automl
# TODO: fix vars as needed
project_id = "covid_mask_identifier"
dataset_id = "covid_id_dataset"
path = "gs://YOUR_BUCKET_ID/path/to/data.csv"
client = automl.AutoMlClient()
# Get the full path of the dataset.
dataset_full_id = client.dataset_path(
project_id, "us-central1", dataset_id
)
# Get the multiple Google Cloud Storage URIs
input_uris = path.split(",")
gcs_source = automl.GcsSource(input_uris=input_uris)
input_config = automl.InputConfig(gcs_source=gcs_source)
# Import data from the input URI
response = client.import_data(name=dataset_full_id, input_config=input_config)
print("Processing import...")
print("Data imported. {}".format(response.result()))