Mixing
The meaning of question mark (?) in keras layers input size
I'm using python2 with keras, tensorflow.
x = Input((32,), name="input1")
I think x's shape is (32,) but print(x) 's result is that 'shape(?,32)'.
What is means of 'shape(?,32)'?
And '?' means what and 32 means what..?
tensorflow keras reshape layer shapes
edited Nov 22 '18 at 9:14
Cleared
1,534923
asked Nov 21 '18 at 6:43
김정화김정화
63
add a comment |
I'm using python2 with keras, tensorflow.
x = Input((32,), name="input1")
I think x's shape is (32,) but print(x) 's result is that 'shape(?,32)'.
What is means of 'shape(?,32)'?
And '?' means what and 32 means what..?
tensorflow keras reshape layer shapes
edited Nov 22 '18 at 9:14
Cleared
1,534923
asked Nov 21 '18 at 6:43
김정화김정화
63
add a comment |
I'm using python2 with keras, tensorflow.
x = Input((32,), name="input1")
I think x's shape is (32,) but print(x) 's result is that 'shape(?,32)'.
What is means of 'shape(?,32)'?
And '?' means what and 32 means what..?
tensorflow keras reshape layer shapes
edited Nov 22 '18 at 9:14
Cleared
1,534923
asked Nov 21 '18 at 6:43
김정화김정화
63
I'm using python2 with keras, tensorflow.
x = Input((32,), name="input1")
I think x's shape is (32,) but print(x) 's result is that 'shape(?,32)'.
What is means of 'shape(?,32)'?
And '?' means what and 32 means what..?
tensorflow keras reshape layer shapes
tensorflow keras reshape layer shapes
edited Nov 22 '18 at 9:14
Cleared
1,534923
asked Nov 21 '18 at 6:43
김정화김정화
63
edited Nov 22 '18 at 9:14
Cleared
1,534923
asked Nov 21 '18 at 6:43
김정화김정화
63
edited Nov 22 '18 at 9:14
Cleared
1,534923
edited Nov 22 '18 at 9:14
Cleared
1,534923
edited Nov 22 '18 at 9:14
Cleared
1,534923
1,534923
asked Nov 21 '18 at 6:43
김정화김정화
63
asked Nov 21 '18 at 6:43
김정화김정화
63
asked Nov 21 '18 at 6:43
김정화김정화
63
63
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
When you define tour input with Input((32,), name="input1") you are telling Keras that each input will be 1-dimensional with size 32. However you might send more than one input during training/predicting. For example if you send in 10 samples, each with length 32, you will actually send in a tensor with shape (10, 32).
Since the topology of the network is not dependent on the number of samples you send in, the shape may vary and is presented as (?,32) where ? is the number of samples.
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
So..(?,32,128) means 2-dimensional with size (32,128) , ? is the number of samples, right?? Do I rightly understand??
– 김정화
Nov 21 '18 at 6:54
Yes, that is correct. For example if your input is images with size 480x360, your input shape will be(?,480,360)since you might send in more than one image each time.
– Cleared
Nov 21 '18 at 6:55
If you have more questions, that is not strictly releated to this question, please create a completely new question instead of taking it here in the comments. That way the question, and the answer to that question, will be much easier to search for and find.
– Cleared
Nov 21 '18 at 6:59
Thank you so much.
– 김정화
Nov 21 '18 at 7:04
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',
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%2f53406545%2fthe-meaning-of-question-mark-in-keras-layers-input-size%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
When you define tour input with Input((32,), name="input1") you are telling Keras that each input will be 1-dimensional with size 32. However you might send more than one input during training/predicting. For example if you send in 10 samples, each with length 32, you will actually send in a tensor with shape (10, 32).
Since the topology of the network is not dependent on the number of samples you send in, the shape may vary and is presented as (?,32) where ? is the number of samples.
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
So..(?,32,128) means 2-dimensional with size (32,128) , ? is the number of samples, right?? Do I rightly understand??
– 김정화
Nov 21 '18 at 6:54
Yes, that is correct. For example if your input is images with size 480x360, your input shape will be(?,480,360)since you might send in more than one image each time.
– Cleared
Nov 21 '18 at 6:55
If you have more questions, that is not strictly releated to this question, please create a completely new question instead of taking it here in the comments. That way the question, and the answer to that question, will be much easier to search for and find.
– Cleared
Nov 21 '18 at 6:59
Thank you so much.
– 김정화
Nov 21 '18 at 7:04
add a comment |
When you define tour input with Input((32,), name="input1") you are telling Keras that each input will be 1-dimensional with size 32. However you might send more than one input during training/predicting. For example if you send in 10 samples, each with length 32, you will actually send in a tensor with shape (10, 32).
Since the topology of the network is not dependent on the number of samples you send in, the shape may vary and is presented as (?,32) where ? is the number of samples.
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
So..(?,32,128) means 2-dimensional with size (32,128) , ? is the number of samples, right?? Do I rightly understand??
– 김정화
Nov 21 '18 at 6:54
Yes, that is correct. For example if your input is images with size 480x360, your input shape will be(?,480,360)since you might send in more than one image each time.
– Cleared
Nov 21 '18 at 6:55
If you have more questions, that is not strictly releated to this question, please create a completely new question instead of taking it here in the comments. That way the question, and the answer to that question, will be much easier to search for and find.
– Cleared
Nov 21 '18 at 6:59
Thank you so much.
– 김정화
Nov 21 '18 at 7:04
add a comment |
When you define tour input with Input((32,), name="input1") you are telling Keras that each input will be 1-dimensional with size 32. However you might send more than one input during training/predicting. For example if you send in 10 samples, each with length 32, you will actually send in a tensor with shape (10, 32).
Since the topology of the network is not dependent on the number of samples you send in, the shape may vary and is presented as (?,32) where ? is the number of samples.
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
When you define tour input with Input((32,), name="input1") you are telling Keras that each input will be 1-dimensional with size 32. However you might send more than one input during training/predicting. For example if you send in 10 samples, each with length 32, you will actually send in a tensor with shape (10, 32).
Since the topology of the network is not dependent on the number of samples you send in, the shape may vary and is presented as (?,32) where ? is the number of samples.
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
answered Nov 21 '18 at 6:51
ClearedCleared
1,534923
1,534923
So..(?,32,128) means 2-dimensional with size (32,128) , ? is the number of samples, right?? Do I rightly understand??
– 김정화
Nov 21 '18 at 6:54
Yes, that is correct. For example if your input is images with size 480x360, your input shape will be(?,480,360)since you might send in more than one image each time.
– Cleared
Nov 21 '18 at 6:55
If you have more questions, that is not strictly releated to this question, please create a completely new question instead of taking it here in the comments. That way the question, and the answer to that question, will be much easier to search for and find.
– Cleared
Nov 21 '18 at 6:59
Thank you so much.
– 김정화
Nov 21 '18 at 7:04
add a comment |
So..(?,32,128) means 2-dimensional with size (32,128) , ? is the number of samples, right?? Do I rightly understand??
– 김정화
Nov 21 '18 at 6:54
Yes, that is correct. For example if your input is images with size 480x360, your input shape will be(?,480,360)since you might send in more than one image each time.
– Cleared
Nov 21 '18 at 6:55
If you have more questions, that is not strictly releated to this question, please create a completely new question instead of taking it here in the comments. That way the question, and the answer to that question, will be much easier to search for and find.
– Cleared
Nov 21 '18 at 6:59
Thank you so much.
– 김정화
Nov 21 '18 at 7:04
So..(?,32,128) means 2-dimensional with size (32,128) , ? is the number of samples, right?? Do I rightly understand??
– 김정화
Nov 21 '18 at 6:54
So..(?,32,128) means 2-dimensional with size (32,128) , ? is the number of samples, right?? Do I rightly understand??
– 김정화
Nov 21 '18 at 6:54
Yes, that is correct. For example if your input is images with size 480x360, your input shape will be
(?,480,360) since you might send in more than one image each time.– Cleared
Nov 21 '18 at 6:55
Yes, that is correct. For example if your input is images with size 480x360, your input shape will be
(?,480,360) since you might send in more than one image each time.– Cleared
Nov 21 '18 at 6:55
If you have more questions, that is not strictly releated to this question, please create a completely new question instead of taking it here in the comments. That way the question, and the answer to that question, will be much easier to search for and find.
– Cleared
Nov 21 '18 at 6:59
If you have more questions, that is not strictly releated to this question, please create a completely new question instead of taking it here in the comments. That way the question, and the answer to that question, will be much easier to search for and find.
– Cleared
Nov 21 '18 at 6:59
Thank you so much.
– 김정화
Nov 21 '18 at 7:04
Thank you so much.
– 김정화
Nov 21 '18 at 7:04
add a comment |
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%2f53406545%2fthe-meaning-of-question-mark-in-keras-layers-input-size%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
