MLeap model prediction time
I have to deploy a machine learning model in a real time system and I found MLeap library which seems to be able to predict an entry in less than 1ms.
I loaded the MLeap model in a Spark app, ran it for like 5000 entries and logged the time for each prediction.
What I find strange here is that the first prediction takes ~50ms and then the time is decreasing until it reaches less than 1 ms for a prediction.
Does anybody know why this is happening? I expected the prediction time to be less than a second for first prediction too.
Thanks
apache-spark machine-learning apache-spark-mllib apache-spark-ml mleap
asked Nov 14 '18 at 14:49
FrodyFrody
537
add a comment |
I have to deploy a machine learning model in a real time system and I found MLeap library which seems to be able to predict an entry in less than 1ms.
I loaded the MLeap model in a Spark app, ran it for like 5000 entries and logged the time for each prediction.
What I find strange here is that the first prediction takes ~50ms and then the time is decreasing until it reaches less than 1 ms for a prediction.
Does anybody know why this is happening? I expected the prediction time to be less than a second for first prediction too.
Thanks
apache-spark machine-learning apache-spark-mllib apache-spark-ml mleap
asked Nov 14 '18 at 14:49
FrodyFrody
537
1
My experiences differ. Apart from startup process in the first few seconds during which i do additional stuff like loading a gigabyte huge dataframe in order to join (own implementation) it to the submitted request-dataframes, the mleap-serving latency was very stable even under heavy load. The delay only happened for me since the time i did this extra stuff during server startup.
– Elmar Macek
Nov 14 '18 at 15:50
add a comment |
I have to deploy a machine learning model in a real time system and I found MLeap library which seems to be able to predict an entry in less than 1ms.
I loaded the MLeap model in a Spark app, ran it for like 5000 entries and logged the time for each prediction.
What I find strange here is that the first prediction takes ~50ms and then the time is decreasing until it reaches less than 1 ms for a prediction.
Does anybody know why this is happening? I expected the prediction time to be less than a second for first prediction too.
Thanks
apache-spark machine-learning apache-spark-mllib apache-spark-ml mleap
asked Nov 14 '18 at 14:49
FrodyFrody
537
I have to deploy a machine learning model in a real time system and I found MLeap library which seems to be able to predict an entry in less than 1ms.
I loaded the MLeap model in a Spark app, ran it for like 5000 entries and logged the time for each prediction.
What I find strange here is that the first prediction takes ~50ms and then the time is decreasing until it reaches less than 1 ms for a prediction.
Does anybody know why this is happening? I expected the prediction time to be less than a second for first prediction too.
Thanks
apache-spark machine-learning apache-spark-mllib apache-spark-ml mleap
apache-spark machine-learning apache-spark-mllib apache-spark-ml mleap
asked Nov 14 '18 at 14:49
FrodyFrody
537
asked Nov 14 '18 at 14:49
FrodyFrody
537
asked Nov 14 '18 at 14:49
FrodyFrody
537
asked Nov 14 '18 at 14:49
FrodyFrody
537
asked Nov 14 '18 at 14:49
FrodyFrody
537
537
1
My experiences differ. Apart from startup process in the first few seconds during which i do additional stuff like loading a gigabyte huge dataframe in order to join (own implementation) it to the submitted request-dataframes, the mleap-serving latency was very stable even under heavy load. The delay only happened for me since the time i did this extra stuff during server startup.
– Elmar Macek
Nov 14 '18 at 15:50
add a comment |
1
My experiences differ. Apart from startup process in the first few seconds during which i do additional stuff like loading a gigabyte huge dataframe in order to join (own implementation) it to the submitted request-dataframes, the mleap-serving latency was very stable even under heavy load. The delay only happened for me since the time i did this extra stuff during server startup.
– Elmar Macek
Nov 14 '18 at 15:50
1
1
My experiences differ. Apart from startup process in the first few seconds during which i do additional stuff like loading a gigabyte huge dataframe in order to join (own implementation) it to the submitted request-dataframes, the mleap-serving latency was very stable even under heavy load. The delay only happened for me since the time i did this extra stuff during server startup.
– Elmar Macek
Nov 14 '18 at 15:50
My experiences differ. Apart from startup process in the first few seconds during which i do additional stuff like loading a gigabyte huge dataframe in order to join (own implementation) it to the submitted request-dataframes, the mleap-serving latency was very stable even under heavy load. The delay only happened for me since the time i did this extra stuff during server startup.
– Elmar Macek
Nov 14 '18 at 15:50
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53302914%2fmleap-model-prediction-time%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53302914%2fmleap-model-prediction-time%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
1
My experiences differ. Apart from startup process in the first few seconds during which i do additional stuff like loading a gigabyte huge dataframe in order to join (own implementation) it to the submitted request-dataframes, the mleap-serving latency was very stable even under heavy load. The delay only happened for me since the time i did this extra stuff during server startup.
– Elmar Macek
Nov 14 '18 at 15:50