[Python] Azure ML - can't use the model path

I'm trying to use the model path, unfortunately I can't. This is the code:

Setting up the environment and correct access:

subscription_id = "xxxxxxxxxxx"
resource_group = "xxxxxxxx"
workspace = "xxxxxxxxxx"

ml_client = MLClient(DefaultAzureCredential(), subscription_id, resource_group, workspace)
ws = ml_client.workspaces.get("xxxxxxxxxx")
print(ws.location, ":", ws.resource_group)


I'm getting confirmation that I'm in the right location and correct resource. Next, I'm registering the model.

from azure.ai.ml.entities import Model
from azure.ai.ml.constants import ModelType

cloud_model = Model(
path="model.pt",
name="model_name",
type="custom",
description="Model created from cloud path."
)
ml_client.models.create_or_update(cloud_model)

latest_model_version = max([int(m.version) for m in ml_client.models.list(name="model_name")])

registered_model = ml_client.models.get(name="model_name", version=latest_model_version)


The code above executed correcly the model have been registered and I can access it. The next block of code is the one, where the issue comes from.

from ultralytics import YOLO

def init():
"""
This function is called when the container is initialized/started, typically after create/update of the deployment.
You can write the logic here to perform init operations like caching the model in memory
"""
global model
# AZUREML_MODEL_DIR is an environment variable created during deployment.
# It is the path to the model folder (./azureml-models/$MODEL_NAME/$VERSION)
model_path = registered_model.path
# deserialize the model file back into a sklearn model
model = YOLO(model_path)
logging.info("Init complete")

init()


The error: FileNotFoundError: [Errno 2] No such file or directory:. Really can't wrap my head arround, how in the previous lines I can access the model and it's path, but I can't use it further down the road?

Continue reading...