Python tensorflow.TensorFlow类代码示例

def test_tf(sagemaker_session, tf_full_version):
    with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
        script_path = os.path.join(DATA_DIR, 'iris', 'iris-dnn-classifier.py')

        estimator = TensorFlow(entry_point=script_path,
                               role='SageMakerRole',
                               framework_version=tf_full_version,
                               training_steps=1,
                               evaluation_steps=1,
                               hyperparameters={'input_tensor_name': 'inputs'},
                               train_instance_count=1,
                               train_instance_type='ml.c4.xlarge',
                               sagemaker_session=sagemaker_session,
                               base_job_name='test-tf')

        inputs = sagemaker_session.upload_data(path=DATA_PATH, key_prefix='integ-test-data/tf_iris')
        estimator.fit(inputs)
        print('job succeeded: {}'.format(estimator.latest_training_job.name))

    endpoint_name = estimator.latest_training_job.name
    with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
        json_predictor = estimator.deploy(initial_instance_count=1, instance_type='ml.c4.xlarge',
                                          endpoint_name=endpoint_name)

        features = [6.4, 3.2, 4.5, 1.5]
        dict_result = json_predictor.predict({'inputs': features})
        print('predict result: {}'.format(dict_result))
        list_result = json_predictor.predict(features)
        print('predict result: {}'.format(list_result))

        assert dict_result == list_result

def test_tf_async(sagemaker_session):
    with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
        script_path = os.path.join(DATA_DIR, 'iris', 'iris-dnn-classifier.py')

        estimator = TensorFlow(entry_point=script_path,
                               role='SageMakerRole',
                               training_steps=1,
                               evaluation_steps=1,
                               hyperparameters={'input_tensor_name': 'inputs'},
                               train_instance_count=1,
                               train_instance_type='ml.c4.xlarge',
                               sagemaker_session=sagemaker_session,
                               base_job_name='test-tf')

        inputs = estimator.sagemaker_session.upload_data(path=DATA_PATH, key_prefix='integ-test-data/tf_iris')
        estimator.fit(inputs, wait=False)
        training_job_name = estimator.latest_training_job.name
        time.sleep(20)

    endpoint_name = training_job_name
    with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
        estimator = TensorFlow.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
        json_predictor = estimator.deploy(initial_instance_count=1, instance_type='ml.c4.xlarge',
                                          endpoint_name=endpoint_name)

        result = json_predictor.predict([6.4, 3.2, 4.5, 1.5])
        print('predict result: {}'.format(result))

def test_failed_tf_training(sagemaker_session, tf_full_version):
    with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
        script_path = os.path.join(DATA_DIR, 'iris', 'failure_script.py')
        ec2_client = sagemaker_session.boto_session.client('ec2')
        subnet, security_group_id = get_or_create_subnet_and_security_group(ec2_client, VPC_NAME)
        estimator = TensorFlow(entry_point=script_path,
                               role='SageMakerRole',
                               framework_version=tf_full_version,
                               training_steps=1,
                               evaluation_steps=1,
                               hyperparameters={'input_tensor_name': 'inputs'},
                               train_instance_count=1,
                               train_instance_type='ml.c4.xlarge',
                               sagemaker_session=sagemaker_session,
                               subnets=[subnet],
                               security_group_ids=[security_group_id])

        inputs = estimator.sagemaker_session.upload_data(path=DATA_PATH, key_prefix='integ-test-data/tf-failure')

        with pytest.raises(ValueError) as e:
            estimator.fit(inputs)
        assert 'This failure is expected' in str(e.value)

        job_desc = estimator.sagemaker_session.sagemaker_client.describe_training_job(
            TrainingJobName=estimator.latest_training_job.name)
        assert [subnet] == job_desc['VpcConfig']['Subnets']
        assert [security_group_id] == job_desc['VpcConfig']['SecurityGroupIds']

def test_cifar(sagemaker_session, tf_full_version):
    with timeout(minutes=45):
        script_path = os.path.join(DATA_DIR, 'cifar_10', 'source')

        dataset_path = os.path.join(DATA_DIR, 'cifar_10', 'data')

        estimator = TensorFlow(entry_point='resnet_cifar_10.py', source_dir=script_path, role='SageMakerRole',
                               framework_version=tf_full_version, training_steps=500, evaluation_steps=5,
                               train_instance_count=2, train_instance_type='ml.p2.xlarge',
                               sagemaker_session=sagemaker_session, train_max_run=45 * 60,
                               base_job_name='test-cifar')

        inputs = estimator.sagemaker_session.upload_data(path=dataset_path, key_prefix='data/cifar10')
        estimator.fit(inputs, logs=False)
        print('job succeeded: {}'.format(estimator.latest_training_job.name))

    endpoint_name = estimator.latest_training_job.name
    with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
        predictor = estimator.deploy(initial_instance_count=1, instance_type='ml.p2.xlarge')
        predictor.serializer = PickleSerializer()
        predictor.content_type = PICKLE_CONTENT_TYPE

        data = np.random.randn(32, 32, 3)
        predict_response = predictor.predict(data)
        assert len(predict_response['outputs']['probabilities']['floatVal']) == 10

def test_train_image_default(sagemaker_session):
    tf = TensorFlow(entry_point=SCRIPT_PATH,
                    role=ROLE,
                    sagemaker_session=sagemaker_session,
                    train_instance_count=INSTANCE_COUNT,
                    train_instance_type=INSTANCE_TYPE)

    assert _get_full_cpu_image_uri(defaults.TF_VERSION) in tf.train_image()

def test_run_tensorboard_locally_without_awscli_binary(time, strftime, popen, call, access, sagemaker_session):
    tf = TensorFlow(entry_point=SCRIPT_PATH, role=ROLE, sagemaker_session=sagemaker_session,
                    train_instance_count=INSTANCE_COUNT, train_instance_type=INSTANCE_TYPE)

    with pytest.raises(EnvironmentError) as error:
        tf.fit(inputs='s3://mybucket/train', run_tensorboard_locally=True)
    assert str(error.value) == 'The AWS CLI is not installed in the system. Please install the AWS CLI using the ' \
                               'following command: \n pip install awscli'

def test_run_tensorboard_locally(sleep, time, strftime, popen, call, access, rmtree, mkdtemp, sync, sagemaker_session):
    tf = TensorFlow(entry_point=SCRIPT_PATH, role=ROLE, sagemaker_session=sagemaker_session,
                    train_instance_count=INSTANCE_COUNT, train_instance_type=INSTANCE_TYPE)

    popen().poll.return_value = None

    tf.fit(inputs='s3://mybucket/train', run_tensorboard_locally=True)

    popen.assert_called_with(['tensorboard', '--logdir', '/my/temp/folder', '--host', 'localhost', '--port', '6006'],
                             stderr=-1,
                             stdout=-1)

def test_run_tensorboard_locally_port_in_use(time, strftime, popen, call, access, socket, rmtree, mkdtemp, sync,
                                             sagemaker_session):
    tf = TensorFlow(entry_point=SCRIPT_PATH, role=ROLE, sagemaker_session=sagemaker_session,
                    train_instance_count=INSTANCE_COUNT, train_instance_type=INSTANCE_TYPE)

    popen().poll.side_effect = [-1, None]

    tf.fit(inputs='s3://mybucket/train', run_tensorboard_locally=True)

    popen.assert_any_call(['tensorboard', '--logdir', '/my/temp/folder', '--host', 'localhost', '--port', '6006'],
                          stderr=-1, stdout=-1)

    popen.assert_any_call(['tensorboard', '--logdir', '/my/temp/folder', '--host', 'localhost', '--port', '6007'],
                          stderr=-1, stdout=-1)

def test_create_model_with_custom_image(sagemaker_session):
    container_log_level = '"logging.INFO"'
    source_dir = 's3://mybucket/source'
    custom_image = 'tensorflow:1.0'
    tf = TensorFlow(entry_point=SCRIPT_PATH, role=ROLE, sagemaker_session=sagemaker_session,
                    training_steps=1000, evaluation_steps=10, train_instance_count=INSTANCE_COUNT,
                    train_instance_type=INSTANCE_TYPE, image_name=custom_image,
                    container_log_level=container_log_level, base_job_name='job',
                    source_dir=source_dir)

    job_name = 'doing something'
    tf.fit(inputs='s3://mybucket/train', job_name=job_name)
    model = tf.create_model()

    assert model.image == custom_image

def test_attach_custom_image(sagemaker_session):
    training_image = '1.dkr.ecr.us-west-2.amazonaws.com/tensorflow_with_custom_binary:1.0'
    rjd = {
        'AlgorithmSpecification': {
            'TrainingInputMode': 'File',
            'TrainingImage': training_image},
        'HyperParameters': {
            'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
            'checkpoint_path': '"s3://other/1508872349"',
            'sagemaker_program': '"iris-dnn-classifier.py"',
            'sagemaker_enable_cloudwatch_metrics': 'false',
            'sagemaker_container_log_level': '"logging.INFO"',
            'sagemaker_job_name': '"neo"',
            'training_steps': '100',
            'evaluation_steps': '10'},
        'RoleArn': 'arn:aws:iam::366:role/SageMakerRole',
        'ResourceConfig': {
            'VolumeSizeInGB': 30,
            'InstanceCount': 1,
            'InstanceType': 'ml.c4.xlarge'},
        'StoppingCondition': {'MaxRuntimeInSeconds': 24 * 60 * 60},
        'TrainingJobName': 'neo',
        'TrainingJobStatus': 'Completed',
        'OutputDataConfig': {'KmsKeyId': '', 'S3OutputPath': 's3://place/output/neo'},
        'TrainingJobOutput': {'S3TrainingJobOutput': 's3://here/output.tar.gz'}}
    sagemaker_session.sagemaker_client.describe_training_job = Mock(name='describe_training_job', return_value=rjd)

    estimator = TensorFlow.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
    assert estimator.image_name == training_image
    assert estimator.train_image() == training_image

def test_failed_tf_training(sagemaker_session, tf_full_version):
    with timeout(minutes=15):
        script_path = os.path.join(DATA_DIR, 'iris', 'failure_script.py')
        estimator = TensorFlow(entry_point=script_path,
                               role='SageMakerRole',
                               framework_version=tf_full_version,
                               training_steps=1,
                               evaluation_steps=1,
                               hyperparameters={'input_tensor_name': 'inputs'},
                               train_instance_count=1,
                               train_instance_type='ml.c4.xlarge',
                               sagemaker_session=sagemaker_session)

        inputs = estimator.sagemaker_session.upload_data(path=DATA_PATH, key_prefix='integ-test-data/tf-failure')

        with pytest.raises(ValueError) as e:
            estimator.fit(inputs)
        assert 'This failure is expected' in str(e.value)

def test_create_model_with_optional_params(sagemaker_session):
    container_log_level = '"logging.INFO"'
    source_dir = 's3://mybucket/source'
    enable_cloudwatch_metrics = 'true'
    tf = TensorFlow(entry_point=SCRIPT_PATH, role=ROLE, sagemaker_session=sagemaker_session,
                    training_steps=1000, evaluation_steps=10, train_instance_count=INSTANCE_COUNT,
                    train_instance_type=INSTANCE_TYPE, container_log_level=container_log_level, base_job_name='job',
                    source_dir=source_dir, enable_cloudwatch_metrics=enable_cloudwatch_metrics)

    job_name = 'doing something'
    tf.fit(inputs='s3://mybucket/train', job_name=job_name)

    new_role = 'role'
    model_server_workers = 2
    model = tf.create_model(role=new_role, model_server_workers=2)

    assert model.role == new_role
    assert model.model_server_workers == model_server_workers

def test_create_model(sagemaker_session, tf_version):
    container_log_level = '"logging.INFO"'
    source_dir = 's3://mybucket/source'
    tf = TensorFlow(entry_point=SCRIPT_PATH, role=ROLE, sagemaker_session=sagemaker_session,
                    training_steps=1000, evaluation_steps=10, train_instance_count=INSTANCE_COUNT,
                    train_instance_type=INSTANCE_TYPE, framework_version=tf_version,
                    container_log_level=container_log_level, base_job_name='job',
                    source_dir=source_dir)

    job_name = 'doing something'
    tf.fit(inputs='s3://mybucket/train', job_name=job_name)
    model = tf.create_model()

    assert model.sagemaker_session == sagemaker_session
    assert model.framework_version == tf_version
    assert model.py_version == tf.py_version
    assert model.entry_point == SCRIPT_PATH
    assert model.role == ROLE
    assert model.name == job_name
    assert model.container_log_level == container_log_level
    assert model.source_dir == source_dir

def test_attach_wrong_framework(sagemaker_session):
    returned_job_description = {
        'AlgorithmSpecification': {
            'TrainingInputMode': 'File',
            'TrainingImage': '1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-mxnet-py2-cpu:1.0'
        },
        'HyperParameters': {
            'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
            'sagemaker_program': '"iris-dnn-classifier.py"',
            'sagemaker_enable_cloudwatch_metrics': 'false',
            'sagemaker_container_log_level': '"logging.INFO"',
            'training_steps': '100'

        },
        'RoleArn': 'arn:aws:iam::366:role/SageMakerRole',
        'ResourceConfig':
            {'VolumeSizeInGB': 30,
             'InstanceCount': 1,
             'InstanceType': 'ml.c4.xlarge'
             },
        'StoppingCondition': {
            'MaxRuntimeInSeconds': 24 * 60 * 60
        },
        'TrainingJobName': 'neo',
        'TrainingJobStatus': 'Completed',
        'OutputDataConfig': {
            'KmsKeyId': '',
            'S3OutputPath': 's3://place/output/neo'
        },
        'TrainingJobOutput': {
            'S3TrainingJobOutput': 's3://here/output.tar.gz'
        }
    }
    sagemaker_session.sagemaker_client.describe_training_job = Mock(name='describe_training_job',
                                                                    return_value=returned_job_description)

    with pytest.raises(ValueError) as error:
        TensorFlow.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
    assert "didn't use image for requested framework" in str(error)

def test_tf(m_tar, e_tar, time, strftime, sagemaker_session, tf_version):
    tf = TensorFlow(entry_point=SCRIPT_FILE, role=ROLE, sagemaker_session=sagemaker_session, training_steps=1000,
                    evaluation_steps=10, train_instance_count=INSTANCE_COUNT, train_instance_type=INSTANCE_TYPE,
                    framework_version=tf_version, requirements_file=REQUIREMENTS_FILE, source_dir=DATA_DIR)

    inputs = 's3://mybucket/train'
    s3_prefix = 's3://{}/{}/source/sourcedir.tar.gz'.format(BUCKET_NAME, JOB_NAME)
    e_tar.return_value = UploadedCode(s3_prefix=s3_prefix, script_name=SCRIPT_FILE)
    s3_prefix = 's3://{}/{}/sourcedir.tar.gz'.format(BUCKET_NAME, JOB_NAME)
    m_tar.return_value = UploadedCode(s3_prefix=s3_prefix, script_name=SCRIPT_FILE)
    tf.fit(inputs=inputs)

    call_names = [c[0] for c in sagemaker_session.method_calls]
    assert call_names == ['train', 'logs_for_job']

    expected_train_args = _create_train_job(tf_version)
    expected_train_args['input_config'][0]['DataSource']['S3DataSource']['S3Uri'] = inputs

    actual_train_args = sagemaker_session.method_calls[0][2]
    assert actual_train_args == expected_train_args

    model = tf.create_model()

    environment = {
        'Environment': {
            'SAGEMAKER_SUBMIT_DIRECTORY': 's3://{}/{}/sourcedir.tar.gz'.format(BUCKET_NAME, JOB_NAME),
            'SAGEMAKER_PROGRAM': 'dummy_script.py', 'SAGEMAKER_REQUIREMENTS': 'dummy_requirements.txt',
            'SAGEMAKER_ENABLE_CLOUDWATCH_METRICS': 'false', 'SAGEMAKER_REGION': 'us-west-2',
            'SAGEMAKER_CONTAINER_LOG_LEVEL': '20'
        },
        'Image': create_image_uri('us-west-2', "tensorflow", INSTANCE_TYPE, tf_version, "py2"),
        'ModelDataUrl': 's3://m/m.tar.gz'
    }
    assert environment == model.prepare_container_def(INSTANCE_TYPE)

    assert 'cpu' in model.prepare_container_def(INSTANCE_TYPE)['Image']
    predictor = tf.deploy(1, INSTANCE_TYPE)
    assert isinstance(predictor, TensorFlowPredictor)