Vertex AI: 予測のために同じ VM 上でモデルを共同ホストする

PROJECT_ID='your-cloud-project' 

BUCKET="gs://${PROJECT_ID}-bucket" gsutil mb -l us-central1 $BUCKET 

import numpy as np  import tensorflow_datasets as tfds import tensorflow as tf  # REPLACE WITH YOUR BUCKET! OUTPUT_PATH='gs://{YOUR_BUCKET}/model_output'  BUFFER_SIZE = 10000 BATCH_SIZE = 64 VOCAB_SIZE = 1000  # Load data dataset, info = tfds.load('imdb_reviews', with_info=True,                           as_supervised=True) train_dataset, test_dataset = dataset['train'], dataset['test']  train_dataset = train_dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE) test_dataset = test_dataset.batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)  # Create text encoder encoder = tf.keras.layers.TextVectorization(     max_tokens=VOCAB_SIZE) encoder.adapt(train_dataset.map(lambda text, label: text))  # Create model model = tf.keras.Sequential([     encoder,     tf.keras.layers.Embedding(         input_dim=len(encoder.get_vocabulary()),         output_dim=64,         # Use masking to handle the variable sequence lengths         mask_zero=True),     tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),     tf.keras.layers.Dense(64, activation='relu'),     tf.keras.layers.Dense(1) ])  # Compile model model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),               optimizer=tf.keras.optimizers.Adam(1e-4),               metrics=['accuracy'])  # Fit model history = model.fit(train_dataset, epochs=10,                     validation_data=test_dataset,                     validation_steps=30)  # Save model model.save(OUTPUT_PATH) 

from google.cloud import aiplatform 

# replace {YOUR_BUCKET} model_1 = aiplatform.Model.upload(display_name='text-model-1',                                   artifact_uri='gs://{YOUR_BUCKET}/model_output',                                   serving_container_image_uri='us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest') 

# replace {YOUR_BUCKET} model_2 = aiplatform.Model.upload(display_name='text-model-2',                                   artifact_uri='gs://{YOUR_BUCKET}/model_output',                                   serving_container_image_uri='us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest') 

endpoint = aiplatform.Endpoint.create('cohost-endpoint') 

# replace {YOUR_PROJECT} PROJECT_ID={YOUR_PROJECT} REGION="us-central1" VERTEX_API_URL=REGION + "-aiplatform.googleapis.com" VERTEX_PREDICTION_API_URL=REGION + "-prediction-aiplatform.googleapis.com" MULTI_MODEL_API_VERSION="v1beta1"  # Give the pool a name DEPLOYMENT_RESOURCE_POOL_ID="my-resource-pool"  import json import pprint pp = pprint.PrettyPrinter(indent=4)  CREATE_RP_PAYLOAD = {   "deployment_resource_pool":{     "dedicated_resources":{       "machine_spec":{         "machine_type":"n1-standard-4"       },       "min_replica_count":1,       "max_replica_count":2     }   },   "deployment_resource_pool_id":DEPLOYMENT_RESOURCE_POOL_ID } CREATE_RP_REQUEST=json.dumps(CREATE_RP_PAYLOAD) pp.pprint("CREATE_RP_REQUEST: " + CREATE_RP_REQUEST)  !curl \ -X POST \ -H "Authorization: Bearer $(gcloud auth print-access-token)" \ -H "Content-Type: application/json" \ https://{VERTEX_API_URL}/{MULTI_MODEL_API_VERSION}/projects/{PROJECT_ID}/locations/{REGION}/deploymentResourcePools \ -d '{CREATE_RP_REQUEST}' 

!curl -X GET \ -H "Authorization: Bearer $(gcloud auth print-access-token)" \ -H "Content-Type: application/json" \ https://{VERTEX_API_URL}/{MULTI_MODEL_API_VERSION}/projects/{PROJECT_ID}/locations/{REGION}/deploymentResourcePools/{DEPLOYMENT_RESOURCE_POOL_ID} 

MODEL_1_ID="{MODEL_1_ID}" ENDPOINT_ID="{ENDPOINT_ID}" 

MODEL_NAME = "projects/{project_id}/locations/{region}/models/{model_id}".format(project_id=PROJECT_ID, region=REGION, model_id=MODEL_1_ID) SHARED_RESOURCE = "projects/{project_id}/locations/{region}/deploymentResourcePools/{deployment_resource_pool_id}".format(project_id=PROJECT_ID, region=REGION, deployment_resource_pool_id=DEPLOYMENT_RESOURCE_POOL_ID)  DEPLOY_MODEL_PAYLOAD = {   "deployedModel": {     "model": MODEL_NAME,     "shared_resources": SHARED_RESOURCE   },   "trafficSplit": {     "0": 100   } } DEPLOY_MODEL_REQUEST=json.dumps(DEPLOY_MODEL_PAYLOAD) pp.pprint("DEPLOY_MODEL_REQUEST: " + DEPLOY_MODEL_REQUEST)  !curl -X POST \  -H "Authorization: Bearer $(gcloud auth print-access-token)" \  -H "Content-Type: application/json" \ https://{VERTEX_API_URL}/{MULTI_MODEL_API_VERSION}/projects/{PROJECT_ID}/locations/{REGION}/endpoints/{ENDPOINT_ID}:deployModel \ -d '{DEPLOY_MODEL_REQUEST}' 

MODEL_2_ID="{MODEL_2_ID}" 

DEPLOYED_MODEL_1_ID = {DEPLOYED_MODEL_1_ID} 

MODEL_NAME = "projects/{project_id}/locations/{region}/models/{model_id}".format(project_id=PROJECT_ID, region=REGION, model_id=MODEL_2_ID) SHARED_RESOURCE = "projects/{project_id}/locations/{region}/deploymentResourcePools/{deployment_resource_pool_id}".format(project_id=PROJECT_ID, region=REGION, deployment_resource_pool_id=DEPLOYMENT_RESOURCE_POOL_ID)  #`trafficSplit` is a map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. # The traffic percentage values for an endpoint must add up to 100. # The key for the model being deployed is "0".  DEPLOY_MODEL_PAYLOAD = {   "deployedModel": {     "model": MODEL_NAME,     "shared_resources": SHARED_RESOURCE   },   "trafficSplit": {     "0": 50,     DEPLOYED_MODEL_1_ID: 50   } } DEPLOY_MODEL_REQUEST=json.dumps(DEPLOY_MODEL_PAYLOAD) pp.pprint("DEPLOY_MODEL_REQUEST: " + DEPLOY_MODEL_REQUEST)  !curl -X POST \  -H "Authorization: Bearer $(gcloud auth print-access-token)" \  -H "Content-Type: application/json" \ https://{VERTEX_API_URL}/{MULTI_MODEL_API_VERSION}/projects/{PROJECT_ID}/locations/{REGION}/endpoints/{ENDPOINT_ID}:deployModel \ -d '{DEPLOY_MODEL_REQUEST}' 

x_test=['The movie was cool. The animation and the graphics were out of this world. I would recommend this movie.'] 

endpoint.predict(instances=x_test)