Hi,
I'm using SKLearn estimator and my inference script contains something like:
def predict_fn(input_data, model):
a = input_data.get('a')
if asset_type and type(a) != str:
raise Exception(f'The asset type must be a string, not {type(asset_type).__name__}')
after running the following code with a false body, e.g. a = [a, b, c]:
client = boto3.client('sagemaker-runtime')
try:
response = client.invoke_endpoint(
EndpointName=endpoint_name,
Body=body,
ContentType='application/json')
except client.exceptions.ModelError as e:
print(e.response)
I get:
{'Error': {'Message': 'Received server error (500) from model with message "<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">\n<title>500 Internal Server Error</title>\n<h1>Internal Server Error</h1>\n<p>The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.</p>\n"..... }
Why can't I see my exception message in the output as written in input_fn? (in the cloudWatch console it is shown)
Thank you
Hi,
I'm using SKLearn estimator and my inference script contains something like:
after running the following code with a false body, e.g. a = [a, b, c]:
I get:
{'Error': {'Message': 'Received server error (500) from model with message "<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">\n<title>500 Internal Server Error</title>\n<h1>Internal Server Error</h1>\n<p>The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.</p>\n"..... }Why can't I see my exception message in the output as written in
input_fn? (in the cloudWatch console it is shown)Thank you