I have fitted a model succefully in Sagemaker with classifier.fit(), I have got success message saying that Finished saving the model.Finished training the model. Script Status - Finished
Now, I tried to deploy the model (make endpoint with the following code.
classifier.deploy(initial_instance_count=1, instance_type='ml.m4.4xlarge')
It initially gave me error.
Error hosting endpoint keras-seq-modelling2021-11-2021-01-07-11-26-56-705: Failed. Reason: The primary container for production variant AllTraffic did not pass the ping health check. Please check CloudWatch logs for this endpoint..
When I looked in logs (cloud watch log stream), It is giving following error.
exec: "serve": executable file not found in $PATH
I know it is relating to making some file executable with granting right permision in some docker container, but the point is that it should be handled by sagemaker and all we need to do according to tutorial is model.deploy()
Am I doing something wrong. Any idea how to resolved this.