Repository navigation
What is the difference between 2 types of xgboost usage? #1946
Description
Hi,
I have a question like this:
What is the difference between
from sagemaker.amazon.amazon_estimator import get_image_uri
container = get_image_uri(region, 'xgboost', '1.0-1')and this
from sagemaker.xgboost.estimator import XGBoost
estimator = XGBoost(entry_point = "your_xgboost_abalone_script.py",
framework_version='1.0-1',
hyperparameters=hyperparameters,
role=sagemaker.get_execution_role(),
train_instance_count=1,
train_instance_type='ml.m5.2xlarge',
output_path=output_path)What is the 2 type of usage difference?
Actually i mostly used sklearn until nowadays. And Sagemaker's logic little push me hard.
Thanks in advance.
Activity
ajaykarpur commentedon Oct 8, 2020
Hi @bilative, which version of the SageMaker Python SDK are you using? You can check the version with
sagemaker.__version__The
get_image_urifunctionality (as well asimage_uris.retrievein v2) is a utility that's used to create the container URI. This functionality is called by theXGBoostclass to construct the container URI.Instead of calling
get_image_uri, you can simply specify theframework_versionas you did in the second code snippet. There is no need to create the URI yourself, as in the first snippet.bilative commentedon Oct 9, 2020
@ajaykarpur Thanks for the suggestion.
I'll think about this.
I checked my version and i saw that "1.72.1" After you said this to me, i realised on the built in xgboost websize SDK1 and SDK2 options of the usage.
Do you know anything about, are there any speed difference between uri version, SDK1 version or SDK2 version. Or there is no difference except usage?
ajaykarpur commentedon Oct 9, 2020
Sure thing. You may also want to take a look at these two documentation pages:
The only differences are related to usage, and these differences are highlighted in the above documentation page. We recommend upgrading to SDK v2. You can do so in the following manner:
pip install --upgrade sagemaker