python - AWS sagemaker 错误 - AttributeError : 'NoneType' object has no attribute 'startswith'

Question

据此 - How to use a pretrained model from s3 to predict some data? ，我试图使用现有模型创建端点，但遇到以下错误 -

    Traceback (most recent call last):
  File "/miniconda3/lib/python3.7/site-packages/gunicorn/workers/base_async.py", line 55, in handle
    self.handle_request(listener_name, req, client, addr)
  File "/miniconda3/lib/python3.7/site-packages/gunicorn/workers/ggevent.py", line 143, in handle_request
    super().handle_request(listener_name, req, sock, addr)
  File "/miniconda3/lib/python3.7/site-packages/gunicorn/workers/base_async.py", line 106, in handle_request
    respiter = self.wsgi(environ, resp.start_response)
  File "/miniconda3/lib/python3.7/site-packages/sagemaker_sklearn_container/serving.py", line 124, in main
    serving_env.module_dir)
  File "/miniconda3/lib/python3.7/site-packages/sagemaker_sklearn_container/serving.py", line 101, in import_module
    user_module = importlib.import_module(module_name)
  File "/miniconda3/lib/python3.7/importlib/__init__.py", line 118, in import_module
    if name.startswith('.'):

根据 Problem deploying the best estimator gotten with sagemaker.estimator.Estimator (w/ sklearn custom image) , https://forums.aws.amazon.com/thread.jspa?threadID=313838 ，我正在使用正确的环境变量(以及 SAGEMAKER_DEFAULT_INVOCATIONS_ACCEPT 、 SAGEMAKER_PROGRAM 和 SAGEMAKER_SUBMIT_DIRECTORY )，但不知何故，在创建端点时运行状况检查失败。
我通过 AWS 控制台尝试了类似的事情，它的工作令人惊讶。
有没有办法通过代码来解决这个问题？
我的代码片段:

trainedmodel = sagemaker.model.Model(
model_data='s3://my-bucket/my-key/output/model.tar.gz',
image='my-image',
env={"SAGEMAKER_DEFAULT_INVOCATIONS_ACCEPT": "text/csv", 
     "SAGEMAKER_USE_NGINX": "True", 
     "SAGEMAKER_WORKER_CLASS_TYPE": "gevent", 
     "SAGEMAKER_KEEP_ALIVE_SEC": "60", 
     "SAGEMAKER_CONTAINER_LOG_LEVEL": "20",
     "SAGEMAKER_ENABLE_CLOUDWATCH_METRICS": "false",
     "SAGEMAKER_PROGRAM": "my-script.py",
     "SAGEMAKER_REGION": "us-east-1",
     "SAGEMAKER_SUBMIT_DIRECTORY": "s3://my-bucket/my-key/source/sourcedir.tar.gz"
    },
role=role)

trainedmodel.deploy(initial_instance_count=1, instance_type='ml.c4.xlarge', endpoint_name = 'my-endpoint')

Answer 1

对于其他登陆这里的人，我在从 ModelPackage 创建 sklearn 模型时遇到了类似的问题。
尝试创建端点时端点日志中的错误消息:

AttributeError: 'NoneType' object has no attribute 'startswith'

在定义模型包时解决了以下问题:

环境变量 SAGEMAKER_SUBMIT_DIRECTORY应设置为容器上的目录，通常为'/opt/ml/model/'

SAGEMAKER_PROGRAM应设置为服务脚本的名称，例如'sagemaker_serve.py'

这些在“容器”部分中每个条目的“环境”部分下指定。