What means mean and stddev in keras/tensorflow

up vote
0
down vote

favorite

in below part of code what means mean and stddev ?
I know the seed is put to 1 so if you generate random values those are always the same. But don't know about mean and stddev?

I know the seed is put on 1 so you should have always the same values generated

    with tf.Session() as test:

    tf.set_random_seed(1)

    y_true = (None, None, None)

    y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1),

              tf.random_normal([3, 128], mean=1, stddev=1, seed = 1),

              tf.random_normal([3, 128], mean=3, stddev=4, seed = 1))

    loss = triplet_loss(y_true, y_pred)



    print("loss = " + str(loss.eval()))

asked Nov 8 at 10:41

Ilse

217

they are the parameters of the normal distribution from which you are sampling
– Russ Hyde
Nov 8 at 10:45

add a comment |

up vote
0
down vote

favorite

in below part of code what means mean and stddev ?
I know the seed is put to 1 so if you generate random values those are always the same. But don't know about mean and stddev?

I know the seed is put on 1 so you should have always the same values generated

    with tf.Session() as test:

    tf.set_random_seed(1)

    y_true = (None, None, None)

    y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1),

              tf.random_normal([3, 128], mean=1, stddev=1, seed = 1),

              tf.random_normal([3, 128], mean=3, stddev=4, seed = 1))

    loss = triplet_loss(y_true, y_pred)



    print("loss = " + str(loss.eval()))

asked Nov 8 at 10:41

Ilse

217

they are the parameters of the normal distribution from which you are sampling
– Russ Hyde
Nov 8 at 10:45

add a comment |

up vote
0
down vote

favorite

in below part of code what means mean and stddev ?
I know the seed is put to 1 so if you generate random values those are always the same. But don't know about mean and stddev?

I know the seed is put on 1 so you should have always the same values generated

    with tf.Session() as test:

    tf.set_random_seed(1)

    y_true = (None, None, None)

    y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1),

              tf.random_normal([3, 128], mean=1, stddev=1, seed = 1),

              tf.random_normal([3, 128], mean=3, stddev=4, seed = 1))

    loss = triplet_loss(y_true, y_pred)



    print("loss = " + str(loss.eval()))

asked Nov 8 at 10:41

Ilse

217

in below part of code what means mean and stddev ?
I know the seed is put to 1 so if you generate random values those are always the same. But don't know about mean and stddev?

I know the seed is put on 1 so you should have always the same values generated

    with tf.Session() as test:

    tf.set_random_seed(1)

    y_true = (None, None, None)

    y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1),

              tf.random_normal([3, 128], mean=1, stddev=1, seed = 1),

              tf.random_normal([3, 128], mean=3, stddev=4, seed = 1))

    loss = triplet_loss(y_true, y_pred)



    print("loss = " + str(loss.eval()))

tensorflow keras conv-neural-network

asked Nov 8 at 10:41

Ilse

217

asked Nov 8 at 10:41

Ilse

217

asked Nov 8 at 10:41

Ilse

217

asked Nov 8 at 10:41

Ilse

217

asked Nov 8 at 10:41

Ilse

217

they are the parameters of the normal distribution from which you are sampling
– Russ Hyde
Nov 8 at 10:45

add a comment |

they are the parameters of the normal distribution from which you are sampling
– Russ Hyde
Nov 8 at 10:45

they are the parameters of the normal distribution from which you are sampling
– Russ Hyde
Nov 8 at 10:45

add a comment |

1 Answer
1

active

oldest

votes

up vote
0
down vote

accepted

Mean is the average of the numbers which will be generated by tf.random_normal(). Similarly, stddev stands for Standard deviation of the data.

if mean=1.2 and stddev=3.4 then, the number matrix generated by tf.random_normal() will have mean and standard deviation as 1.2 and 3.4 respectively.

answered Nov 8 at 11:27

Shubham Panchal

12218

I'm I right if I say that the command y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1) will produce a set of numbers where the mean is 6 and stddev = 0.1 ?
– Ilse
Nov 8 at 11:46

Yes you are absolutely right.
– Shubham Panchal
Nov 8 at 11:53

add a comment |

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',
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
});

}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53206037%2fwhat-means-mean-and-stddev-in-keras-tensorflow%23new-answer', 'question_page');
}
);

Post as a guest

Name

1 Answer
1

active

oldest

votes

1 Answer
1

active

oldest

votes

up vote
0
down vote

accepted

Mean is the average of the numbers which will be generated by tf.random_normal(). Similarly, stddev stands for Standard deviation of the data.

if mean=1.2 and stddev=3.4 then, the number matrix generated by tf.random_normal() will have mean and standard deviation as 1.2 and 3.4 respectively.

answered Nov 8 at 11:27

Shubham Panchal

12218

I'm I right if I say that the command y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1) will produce a set of numbers where the mean is 6 and stddev = 0.1 ?
– Ilse
Nov 8 at 11:46

Yes you are absolutely right.
– Shubham Panchal
Nov 8 at 11:53

add a comment |

up vote
0
down vote

accepted

Mean is the average of the numbers which will be generated by tf.random_normal(). Similarly, stddev stands for Standard deviation of the data.

if mean=1.2 and stddev=3.4 then, the number matrix generated by tf.random_normal() will have mean and standard deviation as 1.2 and 3.4 respectively.

answered Nov 8 at 11:27

Shubham Panchal

12218

I'm I right if I say that the command y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1) will produce a set of numbers where the mean is 6 and stddev = 0.1 ?
– Ilse
Nov 8 at 11:46

Yes you are absolutely right.
– Shubham Panchal
Nov 8 at 11:53

add a comment |

up vote
0
down vote

accepted

Mean is the average of the numbers which will be generated by tf.random_normal(). Similarly, stddev stands for Standard deviation of the data.

if mean=1.2 and stddev=3.4 then, the number matrix generated by tf.random_normal() will have mean and standard deviation as 1.2 and 3.4 respectively.

answered Nov 8 at 11:27

Shubham Panchal

12218

Mean is the average of the numbers which will be generated by tf.random_normal(). Similarly, stddev stands for Standard deviation of the data.

if mean=1.2 and stddev=3.4 then, the number matrix generated by tf.random_normal() will have mean and standard deviation as 1.2 and 3.4 respectively.

answered Nov 8 at 11:27

Shubham Panchal

12218

answered Nov 8 at 11:27

Shubham Panchal

12218

answered Nov 8 at 11:27

Shubham Panchal

12218

answered Nov 8 at 11:27

Shubham Panchal

12218

I'm I right if I say that the command y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1) will produce a set of numbers where the mean is 6 and stddev = 0.1 ?
– Ilse
Nov 8 at 11:46

Yes you are absolutely right.
– Shubham Panchal
Nov 8 at 11:53

add a comment |

I'm I right if I say that the command y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1) will produce a set of numbers where the mean is 6 and stddev = 0.1 ?
– Ilse
Nov 8 at 11:46

Yes you are absolutely right.
– Shubham Panchal
Nov 8 at 11:53

I'm I right if I say that the command y_pred = (tf.random_normal([3, 128], mean=6, stddev=0.1, seed = 1) will produce a set of numbers where the mean is 6 and stddev = 0.1 ?
– Ilse
Nov 8 at 11:46

Yes you are absolutely right.
– Shubham Panchal
Nov 8 at 11:53

add a comment |

draft saved

draft discarded

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Name

This page is only for reference, If you need detailed information, please check here

搜尋此網誌

Xtykutl