I have been playing with Amazon Sagemaker. They have amazing sample notebooks in different areas. However, for testing purposes, I want to create an endpoint that returns the result from a function. From what I have seen so far, my understanding is that we can deploy only models but I would like to clarify it.
Let's say I want to invoke the endpoint and it should give me the square of the input value. So, I will first create a function:
def my_square(x):
return x**2
Can we deploy this simple function in Amazon Sagemaker?
Yes this is possible but it will need some overhead:
You can pass your own docker images for training and inference to sagemaker.
Inside this containers you can do anything you want including return your my_square function. Keep in mind that you have to write your own flask microservice including proxy and wsgi server(if needed).
In my opinion this example is the most helpfull one.
Related
I am looking for a language / framework or a method by which I can build API / web application code such that it can run on Serverless compute's like aws lambda and the same code runs on a dedicated compute system like lightsail or EC2.
First I thought of using Docker to do this but AWS Lambda entry point is a specific function signature which is very different than Spring Controllers. Is there a solution available currently?
So basically when I run it in lambda - it will have cold start issue, later when the app is ready or get popular I would like to move it to a EC2 instance for better performance and higher traffic load.
I want to start right in this situation so that later it can be easy to port and resolve the performance issue's
I'd say; no this is not possible easily.
When you are building an api that you'd want to run on lambda's you most likely will be using an API Gateway which takes care of your routing to different lambda functions (best practice). So the moment you would me working on an api like this migrating to EC2 would be a nightmare as you would need to rebuild the whole application a more of a monolith application which could run on EC2.
I would honestly commit to either run it on EC2/Containers or run it on Lambda, if cold start is your main issue with Lambda's you might wanna look into Lambda Snapstart for Java or use another language like Typescript/Python.
After some correct keywords in google I finally got what I was looking for, checkout this blog and code library shared by AWS which helps you convert the request and response of the request as per the framework required http request
Running APIs Written in Java on AWS Lambda: https://aws.amazon.com/blogs/opensource/java-apis-aws-lambda/
Repo Code: https://github.com/awslabs/aws-serverless-java-container
Thanks Ricardo for your response - will do check out Lambda Snapstart for sure and try it as well. I have not tested out this completely but it looks promising to some extent.
I'm running a training job using AWS SageMaker and i'm using a custom Estimator based on an available docker image from AWS. I wanted to get some feedback on whether my process is correct or not prior to deployment.
I'm running the training job in a docker container using 'local' in a SageMaker notebook instance and the training job runs successfully. However, after the job completes and saves the model to opt/model/models within the docker image, once the docker container exits, the model saved from training is lost. Ideally, i'd like to use the model for inference, however, I'm not sure about the best way of doing it. I have also tried the training job after pushing the image to ECR, but the same thing happens.
It is my understanding that the docker state is lost, once the image exits, as such, is it possible to persist the model that was produced in training in the image? One option I have thought about is saving the model output to an S3 bucket once the training job is complete, then pulling that model into another docker image for inference. Is this expected behaviour and the correct way of doing it?
I am fairly new to using SageMaker but i'd like to do it according to best practices. I've looked at a lot of the AWS documents and followed the tutorials but it doesn't seem to mention explicitly if this is how it should be done.
Thanks for any feedback on this.
You can refer to Rok's comment on saving a model file when you're using a custom estimator. That said, SageMaker built-in estimators save the model artifacts to S3. To make inferences using that model, you can either use a real-time inference endpoint for real time predictions, or a batch transformer to run inferences in batch mode. In both cases, you'll have to point the configuration to the container for inference and the model artifacts. the amazon-sagemaker-examples repository has examples for common frameworks, especially, the scikit-learn example has detailed explanations.
Also, make sure the model is being saved to /opt/ml/model/, not opt/model/models as mentioned in your question.
I am a newbie in AWS. Right now I have defined an image segmentation function in SageMaker notebook instance and this will return masks.
I didn't train my models there, what I have done is pip install models packages there, upload pre-trained weights manually. The rest is very similar to working in local machine: I imported package, load the weights, defined a function to take an image as input then outputs masks.
My question is: is there a way to host my function so that I can call it with URL endpoint + one image info, then it returns me masks in response?
Again I am so new to AWS and I begin to doubt SageMaker is not designed for this job... The reason I chose SageMaker is the need of computing capacity, I don't think I can do this job with pure lambda.
SageMaker inference endpoints currently rely on an interface based on Docker images. At the base level, you can set up a Docker image that runs a web server and responds to the endpoints on the ports that AWS require. This guide will show you how to do it: https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html.
This is an annoying amount of work. If you're using a well-known framework they have a container library that contains some boilerplate code you might be able to reuse: https://github.com/aws/sagemaker-containers. You might have to do some customization there.
Or don't use SageMaker inference endpoints at all :) If your model can fit within the size / memory restrictions of AWS Lambda, that is an easier option!
Full disclaimer, I'm working on a platform that competes with SageMaker: Model Zoo
I have a custom machine learning predictive model. I also have a user defined Estimator class that uses Optuna for hyperparameter tuning. I need to deploy this model to SageMaker so as to invoke it from a lambda function.
I'm facing trouble in the process of creating a container for the model and the Estimator.
I am aware that SageMaker has a scikit learn container which can be used for Optuna, but how would I leverage this to include the functions from my own Estimator class? Also, the model is one of the parameters passed to this Estimator class so how do I define it as a separate training job in order to make it an Endpoint?
This is how the Estimator class and the model are invoked:
sirf_estimator = Estimator(
SIRF, ncov_df, population_dict[countryname],
name=countryname, places=[(countryname, None)],
start_date=critical_country_start
)
sirf_dict = sirf_estimator.run()
where:
Model Name : SIRF
Cleaned Dataset : ncov_df
Would be really helpful if anyone could look into this, thanks a ton!
The SageMaker inference endpoints currently rely on an interface based on Docker images. At the base level, you can set up a Docker image that runs a web server and responds to the endpoints on the ports that AWS require. This guide will show you how to do it: https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html.
This is an annoying amount of work. If you're using a well-known framework they have a container library that contains some boilerplate code you might be able to reuse: https://github.com/aws/sagemaker-containers. You might be able to reuse some code from there, but customize it.
Or don't use SageMaker inference endpoints at all :) If your model can fit within the size / memory restrictions of AWS Lambda, that is an easier option!
I have started exploring AWS SageMaker starting with these examples provided by AWS. I then made some modifications to this particular setup so that it uses the data from my use case for training.
Now, as I continue to work on this model and tuning, after I delete the inference endpoint once, I would like to be able to recreate the same endpoint -- even after stopping and restarting the notebook instance (so the notebook / kernel session is no longer valid) -- using the already trained model artifacts that gets uploaded to S3 under /output folder.
Now I cannot simply jump directly to this line of code:
bt_endpoint = bt_model.deploy(initial_instance_count = 1,instance_type = 'ml.m4.xlarge')
I did some searching -- including amazon's own example of hosting pre-trained models, but I am a little lost. I would appreciate any guidance, examples, or documentation that I could emulate and adapt to my case.
Your comment is correct - you can re-create an Endpoint given an existing EndpointConfiguration. This can be done via the console, the AWS CLI, or the SageMaker boto client.
https://docs.aws.amazon.com/cli/latest/reference/sagemaker/create-endpoint.html
https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.create_endpoint