content_type problem during testing of deployed inferencing endpoint

[xxl4tomxu98]

class StringPredictor(Predictor):
def init(self, endpoint_name, sagemaker_session):
super(StringPredictor, self).init(endpoint_name, sagemaker_session, content_types='text/csv')

model = PyTorchModel(model_data=estimator.model_data,
role = role,
framework_version='1.8.1',
py_version='py36',
entry_point='predict.py',
source_dir='serve',
predictor_cls=StringPredictor)

The error message is:

ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received server error (500) from model with message "Requested unsupported ContentType in content_type: application/octet-stream
Traceback (most recent call last):
File "/opt/conda/lib/python3.6/site-packages/sagemaker_inference/transformer.py", line 126, in transform
result = self._transform_fn(self._model, input_data, content_type, accept)
File "/opt/conda/lib/python3.6/site-packages/sagemaker_inference/transformer.py", line 215, in _default_transform_fn
data = self._input_fn(input_data, content_type)
File "/opt/ml/model/code/predict.py", line 54, in input_fn
raise Exception('Requested unsupported ContentType in content_type: ' + content_type)
Exception: Requested unsupported ContentType in content_type: application/octet-stream
". See https://us-east-1.console.aws.amazon.com/cloudwatch/home?region=us-east-1#logEventViewer:group=/aws/sagemaker/Endpoints/pytorch-inference-2021-08-07-19-02-59-975 in account 804604702169 for more information.

[LiJell]

same here