![](/img/trans.png)
[英]How do I deploy a ML model trained on SageMaker, to a local machine to run predict?
[英]How can I deploy an ML model from ECS to Sagemaker?
我有一個在本地培訓的模型,然后轉移到了AWS ECS。 我想將其部署到Sagemaker。
目前,我正在:
from sagemaker.estimator import Estimator
model = Estimator(image,
role, 1, 'ml.c4.2xlarge',
output_path="s3://{}/output".format(sess.default_bucket()),
sagemaker_session=sess)
但是當我打電話
from sagemaker.predictor import csv_serializer
predictor = agent.deploy(1, 'ml.t2.medium', serializer=csv_serializer)
我得到:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-5-0ca9477e4acb> in <module>()
1 from sagemaker.predictor import csv_serializer
----> 2 predictor = model.deploy(1, 'ml.t2.medium', serializer=csv_serializer)
~/anaconda3/envs/python3/lib/python3.6/site-packages/sagemaker/estimator.py in deploy(self, initial_instance_count, instance_type, endpoint_name, **kwargs)
177 """
178 if not self.latest_training_job:
--> 179 raise RuntimeError('Estimator has not been fit yet.')
180 endpoint_name = endpoint_name or self.latest_training_job.name
181 self.deploy_instance_type = instance_type
RuntimeError: Estimator has not been fit yet.
但這很合適……只是不適合使用Sagemaker。 我該如何克服這個問題?
您可以創建Model
的實例,以將模型部署到未經SageMaker訓練的端點:
mxnet_model = MXNetModel(model_data="s3://bucket/model.tar.gz",
role="SageMakerRole",
entry_point="trasform_script.py")
predictor = mxnet_model.deploy(instance_type="ml.c4.xlarge",
initial_instance_count=1)
GitHub存儲庫https://github.com/awslabs/amazon-sagemaker-examples包含有關如何部署模型的更多示例: https : //github.com/awslabs/amazon-sagemaker-examples/blob/master/advanced_functionality/tensorflow_iris_byom /tensorflow_BYOM_iris.ipynb和https://github.com/awslabs/amazon-sagemaker-examples/tree/master/advanced_functionality/mxnet_mnist_byom
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.