本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# 先决条件
<a name="neo-deployment-hosting-services-prerequisites"></a>

**注意**  
如果您使用 适用于 Python (Boto3) 的 AWS SDK、或 SageMaker AI 控制台编译模型 AWS CLI，请按照本节中的说明进行操作。

要创建 SageMaker Neo 编译的模型，您需要以下内容：

1. Docker 映像 Amazon ECR URI。您可以从[此列表](https://docs.aws.amazon.com/sagemaker/latest/dg/neo-deployment-hosting-services-container-images.html)中选择一个满足您需求的产品。

1. 入口点脚本文件：

   1. **适用于 PyTorch 和 MXNet 型号：**

      *如果您使用 SageMaker AI 训练模型*，则训练脚本必须实现下述功能。训练脚本在推理过程中用作入口点脚本。在 [MNIST 使用 MXNet 模块和 N SageMaker eo 进行训练、编译和部署](https://sagemaker-examples.readthedocs.io/en/latest/sagemaker_neo_compilation_jobs/mxnet_mnist/mxnet_mnist_neo.html)中详述的示例中，训练脚本 (`mnist.py`) 实现了所需的函数。

      *如果您没有使用 SageMaker AI 训练模型*，则需要提供可在推理时使用的入口点脚本 (`inference.py`) 文件。基于框架 PyTorch —— MXNet 或——推理脚本的位置必须符合适用的 SageMaker Python SDK [模型目录结构 MxNet](https://sagemaker.readthedocs.io/en/stable/frameworks/mxnet/using_mxnet.html#model-directory-structure)或[模型目录结构](https://sagemaker.readthedocs.io/en/stable/frameworks/pytorch/using_pytorch.html#model-directory-structure)。 PyTorch

      **MXNet**在 CPU **PyTorch**和 GPU 实例类型上使用 Neo 推理优化的容器镜像时，推理脚本必须实现以下功能：
      + `model_fn`：加载模型。（可选）
      + `input_fn`：将传入的请求负载转换为 numpy 数组。
      + `predict_fn`：执行预测。
      + `output_fn`：将预测输出转换为响应负载。
      + 或者，您可以将 `transform_fn` 定义为组合 `input_fn`、`predict_fn` 和 `output_fn`。

      以下是名为 `code` (`code/inference.py`) **PyTorch 和 MXNet （Gluon and Mod** ule）的目录中的`inference.py`脚本示例。这些示例首先加载模型，然后在 GPU 上将其提供给映像数据：

------
#### [ MXNet Module ]

      ```
      import numpy as np
      import json
      import mxnet as mx
      import neomx  # noqa: F401
      from collections import namedtuple
      
      Batch = namedtuple('Batch', ['data'])
      
      # Change the context to mx.cpu() if deploying to a CPU endpoint
      ctx = mx.gpu()
      
      def model_fn(model_dir):
          # The compiled model artifacts are saved with the prefix 'compiled'
          sym, arg_params, aux_params = mx.model.load_checkpoint('compiled', 0)
          mod = mx.mod.Module(symbol=sym, context=ctx, label_names=None)
          exe = mod.bind(for_training=False,
                         data_shapes=[('data', (1,3,224,224))],
                         label_shapes=mod._label_shapes)
          mod.set_params(arg_params, aux_params, allow_missing=True)
          
          # Run warm-up inference on empty data during model load (required for GPU)
          data = mx.nd.empty((1,3,224,224), ctx=ctx)
          mod.forward(Batch([data]))
          return mod
      
      
      def transform_fn(mod, image, input_content_type, output_content_type):
          # pre-processing
          decoded = mx.image.imdecode(image)
          resized = mx.image.resize_short(decoded, 224)
          cropped, crop_info = mx.image.center_crop(resized, (224, 224))
          normalized = mx.image.color_normalize(cropped.astype(np.float32) / 255,
                                        mean=mx.nd.array([0.485, 0.456, 0.406]),
                                        std=mx.nd.array([0.229, 0.224, 0.225]))
          transposed = normalized.transpose((2, 0, 1))
          batchified = transposed.expand_dims(axis=0)
          casted = batchified.astype(dtype='float32')
          processed_input = casted.as_in_context(ctx)
      
          # prediction/inference
          mod.forward(Batch([processed_input]))
      
          # post-processing
          prob = mod.get_outputs()[0].asnumpy().tolist()
          prob_json = json.dumps(prob)
          return prob_json, output_content_type
      ```

------
#### [ MXNet Gluon ]

      ```
      import numpy as np
      import json
      import mxnet as mx
      import neomx  # noqa: F401
      
      # Change the context to mx.cpu() if deploying to a CPU endpoint
      ctx = mx.gpu()
      
      def model_fn(model_dir):
          # The compiled model artifacts are saved with the prefix 'compiled'
          block = mx.gluon.nn.SymbolBlock.imports('compiled-symbol.json',['data'],'compiled-0000.params', ctx=ctx)
          
          # Hybridize the model & pass required options for Neo: static_alloc=True & static_shape=True
          block.hybridize(static_alloc=True, static_shape=True)
          
          # Run warm-up inference on empty data during model load (required for GPU)
          data = mx.nd.empty((1,3,224,224), ctx=ctx)
          warm_up = block(data)
          return block
      
      
      def input_fn(image, input_content_type):
          # pre-processing
          decoded = mx.image.imdecode(image)
          resized = mx.image.resize_short(decoded, 224)
          cropped, crop_info = mx.image.center_crop(resized, (224, 224))
          normalized = mx.image.color_normalize(cropped.astype(np.float32) / 255,
                                        mean=mx.nd.array([0.485, 0.456, 0.406]),
                                        std=mx.nd.array([0.229, 0.224, 0.225]))
          transposed = normalized.transpose((2, 0, 1))
          batchified = transposed.expand_dims(axis=0)
          casted = batchified.astype(dtype='float32')
          processed_input = casted.as_in_context(ctx)
          return processed_input
      
      
      def predict_fn(processed_input_data, block):
          # prediction/inference
          prediction = block(processed_input_data)
          return prediction
      
      def output_fn(prediction, output_content_type):
          # post-processing
          prob = prediction.asnumpy().tolist()
          prob_json = json.dumps(prob)
          return prob_json, output_content_type
      ```

------
#### [ PyTorch 1.4 and Older ]

      ```
      import os
      import torch
      import torch.nn.parallel
      import torch.optim
      import torch.utils.data
      import torch.utils.data.distributed
      import torchvision.transforms as transforms
      from PIL import Image
      import io
      import json
      import pickle
      
      
      def model_fn(model_dir):
          """Load the model and return it.
          Providing this function is optional.
          There is a default model_fn available which will load the model
          compiled using SageMaker Neo. You can override it here.
      
          Keyword arguments:
          model_dir -- the directory path where the model artifacts are present
          """
      
          # The compiled model is saved as "compiled.pt"
          model_path = os.path.join(model_dir, 'compiled.pt')
          with torch.neo.config(model_dir=model_dir, neo_runtime=True):
              model = torch.jit.load(model_path)
              device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
              model = model.to(device)
      
          # We recommend that you run warm-up inference during model load
          sample_input_path = os.path.join(model_dir, 'sample_input.pkl')
          with open(sample_input_path, 'rb') as input_file:
              model_input = pickle.load(input_file)
          if torch.is_tensor(model_input):
              model_input = model_input.to(device)
              model(model_input)
          elif isinstance(model_input, tuple):
              model_input = (inp.to(device) for inp in model_input if torch.is_tensor(inp))
              model(*model_input)
          else:
              print("Only supports a torch tensor or a tuple of torch tensors")
              return model
      
      
      def transform_fn(model, request_body, request_content_type,
                       response_content_type):
          """Run prediction and return the output.
          The function
          1. Pre-processes the input request
          2. Runs prediction
          3. Post-processes the prediction output.
          """
          # preprocess
          decoded = Image.open(io.BytesIO(request_body))
          preprocess = transforms.Compose([
              transforms.Resize(256),
              transforms.CenterCrop(224),
              transforms.ToTensor(),
              transforms.Normalize(
                  mean=[
                      0.485, 0.456, 0.406], std=[
                      0.229, 0.224, 0.225]),
          ])
          normalized = preprocess(decoded)
          batchified = normalized.unsqueeze(0)
          # predict
          device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
          batchified = batchified.to(device)
          output = model.forward(batchified)
      
          return json.dumps(output.cpu().numpy().tolist()), response_content_type
      ```

------
#### [ PyTorch 1.5 and Newer ]

      ```
      import os
      import torch
      import torch.nn.parallel
      import torch.optim
      import torch.utils.data
      import torch.utils.data.distributed
      import torchvision.transforms as transforms
      from PIL import Image
      import io
      import json
      import pickle
      
      
      def model_fn(model_dir):
          """Load the model and return it.
          Providing this function is optional.
          There is a default_model_fn available, which will load the model
          compiled using SageMaker Neo. You can override the default here.
          The model_fn only needs to be defined if your model needs extra
          steps to load, and can otherwise be left undefined.
      
          Keyword arguments:
          model_dir -- the directory path where the model artifacts are present
          """
      
          # The compiled model is saved as "model.pt"
          model_path = os.path.join(model_dir, 'model.pt')
          device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
          model = torch.jit.load(model_path, map_location=device)
          model = model.to(device)
      
          return model
      
      
      def transform_fn(model, request_body, request_content_type,
                          response_content_type):
          """Run prediction and return the output.
          The function
          1. Pre-processes the input request
          2. Runs prediction
          3. Post-processes the prediction output.
          """
          # preprocess
          decoded = Image.open(io.BytesIO(request_body))
          preprocess = transforms.Compose([
                                      transforms.Resize(256),
                                      transforms.CenterCrop(224),
                                      transforms.ToTensor(),
                                      transforms.Normalize(
                                          mean=[
                                              0.485, 0.456, 0.406], std=[
                                              0.229, 0.224, 0.225]),
                                          ])
          normalized = preprocess(decoded)
          batchified = normalized.unsqueeze(0)
          
          # predict
          device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
          batchified = batchified.to(device)
          output = model.forward(batchified)
          return json.dumps(output.cpu().numpy().tolist()), response_content_type
      ```

------

   1.  **对于 inf1 实例或 onnx、xgboost、keras 容器映像** 

      对于所有其他 Neo Inference 优化的容器映像或 inferentia 实例类型，入口点脚本必须为 Neo 深度学习运行时系统实施以下功能：
      + `neo_preprocess`：将传入的请求负载转换为 numpy 数组。
      + `neo_postprocess`：将 Neo 深度学习运行时系统的预测输出转换为响应正文。
**注意**  
前两个函数不使用 MXNet PyTorch、或 TensorFlow的任何功能。

      有关如何使用这些功能的示例，请参阅 [Neo 模型编译示例笔记本](https://docs.aws.amazon.com//sagemaker/latest/dg/neo.html#neo-sample-notebooks)。

   1. **对于 TensorFlow 模特**

      如果您的模型在将数据发送到模型之前需要自定义的预处理和后处理逻辑，则必须指定推理时可以使用的入口点脚本 `inference.py` 文件。该脚本应实施一对 `input_handler` 和 `output_handler` 功能或单个处理程序功能。
**注意**  
请注意，如果处理程序功能已实施，则 `input_handler` 和 `output_handler` 被忽略。

      以下是 `inference.py` 脚本的代码示例，您可以将该脚本与编译模型组合在一起，对图像分类模型执行自定义的预处理和后处理。A SageMaker I 客户端将图像文件作为`application/x-image`内容类型发送给`input_handler`函数，然后将其转换为 JSON。然后，使用 REST API 将转换后的映像文件发送到 [Tensorflow Model Server (TFX)](https://www.tensorflow.org/tfx/serving/api_rest)。

      ```
      import json
      import numpy as np
      import json
      import io
      from PIL import Image
      
      def input_handler(data, context):
          """ Pre-process request input before it is sent to TensorFlow Serving REST API
          
          Args:
          data (obj): the request data, in format of dict or string
          context (Context): an object containing request and configuration details
          
          Returns:
          (dict): a JSON-serializable dict that contains request body and headers
          """
          f = data.read()
          f = io.BytesIO(f)
          image = Image.open(f).convert('RGB')
          batch_size = 1
          image = np.asarray(image.resize((512, 512)))
          image = np.concatenate([image[np.newaxis, :, :]] * batch_size)
          body = json.dumps({"signature_name": "serving_default", "instances": image.tolist()})
          return body
      
      def output_handler(data, context):
          """Post-process TensorFlow Serving output before it is returned to the client.
          
          Args:
          data (obj): the TensorFlow serving response
          context (Context): an object containing request and configuration details
          
          Returns:
          (bytes, string): data to return to client, response content type
          """
          if data.status_code != 200:
              raise ValueError(data.content.decode('utf-8'))
      
          response_content_type = context.accept_header
          prediction = data.content
          return prediction, response_content_type
      ```

      如果没有自定义的预处理或后处理， SageMaker AI 客户端会以类似的方式将文件图像转换为 JSON，然后再将其发送到 SageMaker AI 终端节点。

      有关更多信息，请参阅 [ SageMaker Python SDK 中的部署到 TensorFlow 服务端点](https://sagemaker.readthedocs.io/en/stable/frameworks/tensorflow/deploying_tensorflow_serving.html#providing-python-scripts-for-pre-pos-processing)。

1. 包含已编译模型构件的 Amazon S3 存储桶 URI。