将自定义训练的 Keras 模型与 Sagemaker 端点结合使用会导致 ModelError：调用 InvokeEndpoint 操作时发生错误 (ModelError)：

Question

我试图通过在 sagemaker 中加载预先训练的模型来进行预测，但出现以下错误

ModelError：调用时发生错误（ModelError） InvokeEndpoint 操作：从主服务器收到客户端错误 (400) 消息 "{ "error": "之前未使用图表创建会话 运行（）！” }

我的代码

def convert_h5_to_aws(loaded_model):
    import tensorflow as tf
    if tf.executing_eagerly():
        tf.compat.v1.disable_eager_execution()
    """
    given a pre-trained keras model, this function converts it to a TF protobuf format
    and saves it in the file structure which aws expects
    """  
    from tensorflow.python.saved_model import builder
    from tensorflow.python.saved_model.signature_def_utils import predict_signature_def
    from tensorflow.python.saved_model import tag_constants
    
    # This is the file structure which AWS expects. Cannot be changed. 
    model_version = '1'
    export_dir = 'export/Servo/' + model_version
    
    # Build the Protocol Buffer SavedModel at 'export_dir'
    builder = builder.SavedModelBuilder(export_dir)
    
    # Create prediction signature to be used by TensorFlow Serving Predict API
    signature = predict_signature_def(
        inputs={"inputs": loaded_model.input}, outputs={"score":    loaded_model.output})
    
    from keras import backend as K
    with K.get_session() as sess:
        # Save the meta graph and variables
        builder.add_meta_graph_and_variables(
            sess=sess, tags=[tag_constants.SERVING], signature_def_map={"serving_default": signature})
        builder.save()
    
    #create a tarball/tar file and zip it
    import tarfile
    with tarfile.open('model.tar.gz', mode='w:gz') as archive:
        archive.add('export', recursive=True)
        
convert_h5_to_aws(model)



import sagemaker

sagemaker_session = sagemaker.Session()
inputs = sagemaker_session.upload_data(path='model.tar.gz', key_prefix='model')

!touch train.py #create an empty python file
import boto3, re
from sagemaker import get_execution_role

# the (default) IAM role you created when creating this notebook
role = get_execution_role()
import boto3, re
from sagemaker import get_execution_role

# the (default) IAM role you created when creating this notebook
role = get_execution_role()

# Create a Sagemaker model (see AWS console>SageMaker>Models)
from sagemaker.tensorflow.model import TensorFlowModel
sagemaker_model = TensorFlowModel(model_data = 's3://' + sagemaker_session.default_bucket() + '/model/model.tar.gz',
                                  role = role,
                                  framework_version = '1.12',
                                  entry_point = 'train.py')


# Deploy a SageMaker to an endpoint
predictor = sagemaker_model.deploy(initial_instance_count=1,
                                   instance_type='ml.m4.xlarge')
                                 

# Create a predictor which uses this new endpoint
import sagemaker
from sagemaker.tensorflow.model import TensorFlowModel

#endpoint = '' #get endpoint name from SageMaker > endpoints

predictor=sagemaker.tensorflow.model.TensorFlowPredictor(endpoint, sagemaker_session)
# .predict send the data to our endpoint
data = X_test #<-- update this to have inputs for your model
predictor.predict(data)

我也尝试使用不同版本的 TensorFlowModel

Answer 1

所有这些代码都在笔记本中吗？您需要确保正确保存模型工件和推理代码。确保正确存储已保存模型的元数据，并且如果您有带有推理函数的推理脚本（处理预处理和后处理），则该脚本也应该与 tar 文件中的脚本一起包装在代码目录中。以下是在 SageMaker 上部署预训练的 Sklearn 模型的示例，您可以对预训练的 TensorFlow 模型执行相同的操作。

Sklearn 预训练示例：https://github.com/RamVegiraju/Pre-Trained- Sklearn-SageMaker