Sagemaker本地部署：“RuntimeError: Giving up, endpoint: didn't launch correctly”

Question

【以下的问题经过翻译处理】 你好，
我正在尝试在本地启动一个endpoint，从我的开发notebook上进行一些推理（无需等待实际端点的实例化时间或批量训练）。我正在运行以下代码：

```
# get trained model from s3
trained_S2S = SM.model.Model(
    image = seq2seq，
    model_data =（'s3://XXXXXXXXXXXXX/'
        +'output/seq2seq-2018-07-30-16-55-12-521/output/model.tar.gz'），
    role = role) 
S2S = trained_S2S.deploy(1, instance_type = 'local')   
```
我得到以下错误（重复了几百行）：

```
WARNING:urllib3.connectionpool:Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 111] Connection refused',)': /ping

```
```
RuntimeError: Giving up, endpoint: seq2seq-2018-08-01-14-18-06-555 didn't launch correctly
```

Answer

【以下的回答经过翻译处理】 目前，SageMaker本地仅支持SageMaker框架容器（MXNet、TensorFlow、PyTorch、Chainer和Spark），不支持内置算法。

Sagemaker本地部署：“RuntimeError: Giving up, endpoint: didn't launch correctly”

Relevanter Inhalt