SAM inference on SageMaker

#3
by francisurias - opened

Hi,

I'm trying to deploy SAM as a SageMaker endpoint; I've managed to deploy SAM as a SageMaker endpoint using the given deployment code (found below), but I'm having difficulty doing the inference to the endpoint because I'm unsure what the input for the endpoint is, is there an example input I can try to do SAM inference on SageMaker?

Thanks for the help!

import sagemaker
import boto3
from sagemaker.huggingface import HuggingFaceModel

try:
    role = sagemaker.get_execution_role()
except ValueError:
    iam = boto3.client('iam')
    role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']

# Hub Model configuration. https://huggingface.co./models
hub = {
    'HF_MODEL_ID':'facebook/sam-vit-large',
    'HF_TASK':'undefined'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
    transformers_version='4.26.0',
    pytorch_version='1.13.1',
    py_version='py39',
    env=hub,
    role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
    initial_instance_count=1, # number of instances
    instance_type='ml.m5.xlarge' # ec2 instance type
)

I have the issue, any solution?

Sign up or log in to comment