Panduan ini memberikan alur kerja end-to-end lengkap untuk melatih model dan mengklasifikasikan aset gambar menggunakan platform Vertex AI Google Cloud dengan Gemini 2.5 Flash. Anda akan mempelajari cara mengintegrasikan BigQuery untuk pengambilan data, Cloud Storage untuk pengelolaan aset, dan Vertex AI untuk inferensi machine learning di lingkungan Python Colab.
Konfigurasi
Tetapkan variabel khusus project berikut sebelum menjalankan contoh kode:
PROJECT_ID = "PROJECT_ID"
REGION = "REGION " # e.g., "us-central1"
LOCATION = "LOCATION " # e.g., "us"
CUSTOMER_ID = "CUSTOMER_ID" # required to subscribe to the dataset
Penyiapan Lingkungan
Instal dependensi yang diperlukan dan konfigurasi autentikasi untuk mengakses layanan Google Cloud:
# Install Google Cloud SDK dependencies for AI Platform integration
!pip install google-cloud-aiplatform google-cloud-storage google-cloud-bigquery google-cloud-bigquery-data-exchange -q
# Import core libraries for cloud services and machine learning operations
import json
import os
from google.cloud import bigquery
import vertexai
from vertexai.generative_models import GenerativeModel, Part
# Configure authentication for Google Cloud service access
# Initiates OAuth flow in new browser tab if authentication required
from google.colab import auth
if os.environ.get("VERTEX_PRODUCT") != "COLAB_ENTERPRISE":
from google.colab import auth
auth.authenticate_user(project_id=PROJECT_ID)
# Initialize Vertex AI client with project configuration
vertexai.init(project=PROJECT_ID, location=REGION)
print(f"Vertex AI initialized for project: {PROJECT_ID} in region: {REGION}")
Berlangganan set data Analytics Hub
Anda juga harus berlangganan set data Analytics Hub.
from google.cloud import bigquery_data_exchange_v1beta1
ah_client = bigquery_data_exchange_v1beta1.AnalyticsHubServiceClient()
HUB_PROJECT_ID = 'maps-platform-analytics-hub'
DATA_EXCHANGE_ID = f"imagery_insights_exchange_{LOCATION}"
LINKED_DATASET_NAME = f"imagery_insights___preview___{LOCATION}"
# subscribe to the listing (create a linked dataset in your consumer project)
destination_dataset = bigquery_data_exchange_v1beta1.DestinationDataset()
destination_dataset.dataset_reference.dataset_id = LINKED_DATASET_NAME
destination_dataset.dataset_reference.project_id = PROJECT_ID
destination_dataset.location = LOCATION
LISTING_ID=f"imagery_insights_{CUSTOMER_ID.replace('-', '_')}__{LOCATION}"
published_listing = f"projects/{HUB_PROJECT_ID}/locations/{LOCATION}/dataExchanges/{DATA_EXCHANGE_ID}/listings/{LISTING_ID}"
request = bigquery_data_exchange_v1beta1.SubscribeListingRequest(
destination_dataset=destination_dataset,
name=published_listing,
)
# request the subscription
ah_client.subscribe_listing(request=request)
Ekstraksi Data dengan BigQuery
Jalankan kueri BigQuery untuk mengekstrak URI Google Cloud Storage dari tabel latest_observations. URI ini akan diteruskan langsung ke model Vertex AI untuk klasifikasi.
# Initialize BigQuery client
bigquery_client = bigquery.Client(project=PROJECT_ID)
# Define SQL query to retrieve observation records from imagery dataset
query = f"""
SELECT
*
FROM
`{PROJECT_ID}.imagery_insights___preview___{LOCATION}.latest_observations`
LIMIT 10;
"""
print(f"Executing BigQuery query:\n{query}")
# Submit query job to BigQuery service and await completion
query_job = bigquery_client.query(query)
# Transform query results into structured data format for downstream processing
# Convert BigQuery Row objects to dictionary representations for enhanced accessibility
query_response_data = []
for row in query_job:
query_response_data.append(dict(row))
# Extract Cloud Storage URIs from result set, filtering null values
gcs_uris = [item.get("gcs_uri") for item in query_response_data if item.get("gcs_uri")]
print(f"BigQuery query returned {len(query_response_data)} records.")
print(f"Extracted {len(gcs_uris)} GCS URIs:")
for uri in gcs_uris:
print(uri)
Fungsi Klasifikasi Gambar
Fungsi bantuan ini menangani klasifikasi gambar menggunakan model Gemini 2.5 Flash Vertex AI:
def classify_image_with_gemini(gcs_uri: str, prompt: str = "What is in this image?") -> str:
"""
Performs multimodal image classification using Vertex AI's Gemini 2.5 Flash model.
Leverages direct Cloud Storage integration to process image assets without local
download requirements, enabling scalable batch processing workflows.
Args:
gcs_uri (str): Fully qualified Google Cloud Storage URI
(format: gs://bucket-name/path/to/image.jpg)
prompt (str): Natural language instruction for classification task execution
Returns:
str: Generated textual description from the generative model, or error message
if classification pipeline fails
Raises:
Exception: Captures service-level errors and returns structured failure response
"""
try:
# Instantiate Gemini 2.5 Flash model for inference operations
model = GenerativeModel("gemini-2.5-flash")
# Construct multimodal Part object from Cloud Storage reference
# Note: MIME type may need dynamic inference for mixed image formats
image_part = Part.from_uri(uri=gcs_uri, mime_type="image/jpeg")
# Execute multimodal inference request with combined visual and textual inputs
responses = model.generate_content([image_part, prompt])
return responses.text
except Exception as e:
print(f"Error classifying image from URI {gcs_uri}: {e}")
return "Classification failed."
Klasifikasi Gambar Batch
Memproses semua URI yang diekstrak dan membuat klasifikasi:
classification_results = []
# Execute batch classification pipeline across all extracted GCS URIs
for uri in gcs_uris:
print(f"\nProcessing: {uri}")
# Define comprehensive classification prompt for detailed feature extraction
classification_prompt = "Describe this image in detail, focusing on any objects, signs, or features visible."
# Invoke Gemini model for multimodal inference on current asset
result = classify_image_with_gemini(uri, classification_prompt)
# Aggregate structured results for downstream analytics and reporting
classification_results.append({"gcs_uri": uri, "classification": result})
print(f"Classification for {uri}:\n{result}")
Langkah Berikutnya
Setelah gambar Anda diklasifikasikan, pertimbangkan alur kerja lanjutan berikut:
- Penyesuaian Model: Gunakan hasil klasifikasi untuk melatih model kustom.
- Pemrosesan Otomatis: Siapkan Cloud Functions untuk mengklasifikasikan gambar baru secara otomatis.
- Analisis Data: Lakukan analisis statistik pada pola klasifikasi.
- Integrasi: Hubungkan hasil ke aplikasi downstream.
Pemecahan masalah
Masalah umum dan solusinya:
- Error autentikasi: Pastikan peran IAM dan pengaktifan API sudah tepat.
- Pembatasan frekuensi: Terapkan backoff eksponensial untuk batch besar.
- Batasan memori: Proses gambar dalam batch yang lebih kecil untuk set data besar.
- Error format URI: Pastikan URI GCS mengikuti format
gs://bucket-name/path/to/image.
Untuk dukungan tambahan, lihat dokumentasi Vertex AI dan dokumentasi BigQuery.