Keras: input with size x*x generates unwanted output y*x
I have the following neural network in Keras:
inp = layers.Input((3,))
#Middle layers omitted
out_prop = layers.Dense(units=3, activation='softmax')(inp)
out_value = layers.Dense(units=1, activation = 'linear')(inp)
Then I prepared a pseudo-input to test my network:
inpu = np.array([[1,2,3],[4,5,6],[7,8,9]])
When I try to predict, this happens:
In [45]:nn.network.predict(inpu)
Out[45]:
[array([[0.257513 , 0.41672954, 0.32575747],
[0.20175152, 0.4763418 , 0.32190666],
[0.15986516, 0.53449154, 0.30564335]], dtype=float32),
array([[-0.24281949],
[-0.10461146],
[ 0.11201331]], dtype=float32)]
So, as you can see above, I wanted two output: one should have been an array with size 3, the other should have been a normal value. Instead, I get a 3x3 matrix, and an array with 3 elements. What am I doing wrong?
python machine-learning keras neural-network keras-layer
add a comment |
I have the following neural network in Keras:
inp = layers.Input((3,))
#Middle layers omitted
out_prop = layers.Dense(units=3, activation='softmax')(inp)
out_value = layers.Dense(units=1, activation = 'linear')(inp)
Then I prepared a pseudo-input to test my network:
inpu = np.array([[1,2,3],[4,5,6],[7,8,9]])
When I try to predict, this happens:
In [45]:nn.network.predict(inpu)
Out[45]:
[array([[0.257513 , 0.41672954, 0.32575747],
[0.20175152, 0.4763418 , 0.32190666],
[0.15986516, 0.53449154, 0.30564335]], dtype=float32),
array([[-0.24281949],
[-0.10461146],
[ 0.11201331]], dtype=float32)]
So, as you can see above, I wanted two output: one should have been an array with size 3, the other should have been a normal value. Instead, I get a 3x3 matrix, and an array with 3 elements. What am I doing wrong?
python machine-learning keras neural-network keras-layer
add a comment |
I have the following neural network in Keras:
inp = layers.Input((3,))
#Middle layers omitted
out_prop = layers.Dense(units=3, activation='softmax')(inp)
out_value = layers.Dense(units=1, activation = 'linear')(inp)
Then I prepared a pseudo-input to test my network:
inpu = np.array([[1,2,3],[4,5,6],[7,8,9]])
When I try to predict, this happens:
In [45]:nn.network.predict(inpu)
Out[45]:
[array([[0.257513 , 0.41672954, 0.32575747],
[0.20175152, 0.4763418 , 0.32190666],
[0.15986516, 0.53449154, 0.30564335]], dtype=float32),
array([[-0.24281949],
[-0.10461146],
[ 0.11201331]], dtype=float32)]
So, as you can see above, I wanted two output: one should have been an array with size 3, the other should have been a normal value. Instead, I get a 3x3 matrix, and an array with 3 elements. What am I doing wrong?
python machine-learning keras neural-network keras-layer
I have the following neural network in Keras:
inp = layers.Input((3,))
#Middle layers omitted
out_prop = layers.Dense(units=3, activation='softmax')(inp)
out_value = layers.Dense(units=1, activation = 'linear')(inp)
Then I prepared a pseudo-input to test my network:
inpu = np.array([[1,2,3],[4,5,6],[7,8,9]])
When I try to predict, this happens:
In [45]:nn.network.predict(inpu)
Out[45]:
[array([[0.257513 , 0.41672954, 0.32575747],
[0.20175152, 0.4763418 , 0.32190666],
[0.15986516, 0.53449154, 0.30564335]], dtype=float32),
array([[-0.24281949],
[-0.10461146],
[ 0.11201331]], dtype=float32)]
So, as you can see above, I wanted two output: one should have been an array with size 3, the other should have been a normal value. Instead, I get a 3x3 matrix, and an array with 3 elements. What am I doing wrong?
python machine-learning keras neural-network keras-layer
python machine-learning keras neural-network keras-layer
edited Nov 21 '18 at 12:22
today
11.3k22239
11.3k22239
asked Nov 21 '18 at 11:58
Federico DoratoFederico Dorato
4211
4211
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
You are passing three input samples to the network:
>>> inpu.shape
(3,3) # three samples of size 3
And you have two output layers: one of them outputs a vector of size 3 for each sample and the other outputs a vector of size one (i.e. scalar), again for each sample. As a result the output shapes would be (3, 3)
and (3, 1)
.
Update: If you want your network to accept an input sample of shape (3,3)
and outputs vectors of size 3 and 1, and you want to only use Dense layers in your network, then you must use a Flatten
layer somewhere in the model. One possible option is to use it right after the input layer:
inp = layers.Input((3,3)) # don't forget to set the correct input shape
x = Flatten()(inp)
# pass x to other Dense layers
Alternatively, you could flatten your data to have a shape of (num_samples, 9)
and then pass it to your network without using a Flatten
layer.
Update 2: As @Mete correctly pointed out in the comments, make sure the input array have a shape of (num_samples, 3, 3)
if each input sample has a shape of (3,3)
.
I don't want to have in input 3 samples of size 3. I want to have one sample of size 3x3. Could you tell me how to do that?
– Federico Dorato
Nov 21 '18 at 12:22
@FedericoDorato Please see my updated answer.
– today
Nov 21 '18 at 12:28
inp = layers.Input((3,3))
means every sample is 3x3inpu = np.array([[[1,2,3],[4,5,6],[7,8,9]]])
(note shape is 1x3x3) means you have 1 sample of 3x3 data
– Mete Han Kahraman
Nov 21 '18 at 12:29
@FedericoDorato Please see the second update.
– today
Nov 21 '18 at 12:35
@today i am forced to follow this: "Alternatively, you could flatten your data to have a shape of (num_samples, 9) and then pass it to your network without using a Flatten layer." Because otherwise there is this error: 'Tensor' object has no attribute 'lower'
– Federico Dorato
Nov 30 '18 at 15:05
|
show 1 more 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%2f53411566%2fkeras-input-with-size-xx-generates-unwanted-output-yx%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
You are passing three input samples to the network:
>>> inpu.shape
(3,3) # three samples of size 3
And you have two output layers: one of them outputs a vector of size 3 for each sample and the other outputs a vector of size one (i.e. scalar), again for each sample. As a result the output shapes would be (3, 3)
and (3, 1)
.
Update: If you want your network to accept an input sample of shape (3,3)
and outputs vectors of size 3 and 1, and you want to only use Dense layers in your network, then you must use a Flatten
layer somewhere in the model. One possible option is to use it right after the input layer:
inp = layers.Input((3,3)) # don't forget to set the correct input shape
x = Flatten()(inp)
# pass x to other Dense layers
Alternatively, you could flatten your data to have a shape of (num_samples, 9)
and then pass it to your network without using a Flatten
layer.
Update 2: As @Mete correctly pointed out in the comments, make sure the input array have a shape of (num_samples, 3, 3)
if each input sample has a shape of (3,3)
.
I don't want to have in input 3 samples of size 3. I want to have one sample of size 3x3. Could you tell me how to do that?
– Federico Dorato
Nov 21 '18 at 12:22
@FedericoDorato Please see my updated answer.
– today
Nov 21 '18 at 12:28
inp = layers.Input((3,3))
means every sample is 3x3inpu = np.array([[[1,2,3],[4,5,6],[7,8,9]]])
(note shape is 1x3x3) means you have 1 sample of 3x3 data
– Mete Han Kahraman
Nov 21 '18 at 12:29
@FedericoDorato Please see the second update.
– today
Nov 21 '18 at 12:35
@today i am forced to follow this: "Alternatively, you could flatten your data to have a shape of (num_samples, 9) and then pass it to your network without using a Flatten layer." Because otherwise there is this error: 'Tensor' object has no attribute 'lower'
– Federico Dorato
Nov 30 '18 at 15:05
|
show 1 more comment
You are passing three input samples to the network:
>>> inpu.shape
(3,3) # three samples of size 3
And you have two output layers: one of them outputs a vector of size 3 for each sample and the other outputs a vector of size one (i.e. scalar), again for each sample. As a result the output shapes would be (3, 3)
and (3, 1)
.
Update: If you want your network to accept an input sample of shape (3,3)
and outputs vectors of size 3 and 1, and you want to only use Dense layers in your network, then you must use a Flatten
layer somewhere in the model. One possible option is to use it right after the input layer:
inp = layers.Input((3,3)) # don't forget to set the correct input shape
x = Flatten()(inp)
# pass x to other Dense layers
Alternatively, you could flatten your data to have a shape of (num_samples, 9)
and then pass it to your network without using a Flatten
layer.
Update 2: As @Mete correctly pointed out in the comments, make sure the input array have a shape of (num_samples, 3, 3)
if each input sample has a shape of (3,3)
.
I don't want to have in input 3 samples of size 3. I want to have one sample of size 3x3. Could you tell me how to do that?
– Federico Dorato
Nov 21 '18 at 12:22
@FedericoDorato Please see my updated answer.
– today
Nov 21 '18 at 12:28
inp = layers.Input((3,3))
means every sample is 3x3inpu = np.array([[[1,2,3],[4,5,6],[7,8,9]]])
(note shape is 1x3x3) means you have 1 sample of 3x3 data
– Mete Han Kahraman
Nov 21 '18 at 12:29
@FedericoDorato Please see the second update.
– today
Nov 21 '18 at 12:35
@today i am forced to follow this: "Alternatively, you could flatten your data to have a shape of (num_samples, 9) and then pass it to your network without using a Flatten layer." Because otherwise there is this error: 'Tensor' object has no attribute 'lower'
– Federico Dorato
Nov 30 '18 at 15:05
|
show 1 more comment
You are passing three input samples to the network:
>>> inpu.shape
(3,3) # three samples of size 3
And you have two output layers: one of them outputs a vector of size 3 for each sample and the other outputs a vector of size one (i.e. scalar), again for each sample. As a result the output shapes would be (3, 3)
and (3, 1)
.
Update: If you want your network to accept an input sample of shape (3,3)
and outputs vectors of size 3 and 1, and you want to only use Dense layers in your network, then you must use a Flatten
layer somewhere in the model. One possible option is to use it right after the input layer:
inp = layers.Input((3,3)) # don't forget to set the correct input shape
x = Flatten()(inp)
# pass x to other Dense layers
Alternatively, you could flatten your data to have a shape of (num_samples, 9)
and then pass it to your network without using a Flatten
layer.
Update 2: As @Mete correctly pointed out in the comments, make sure the input array have a shape of (num_samples, 3, 3)
if each input sample has a shape of (3,3)
.
You are passing three input samples to the network:
>>> inpu.shape
(3,3) # three samples of size 3
And you have two output layers: one of them outputs a vector of size 3 for each sample and the other outputs a vector of size one (i.e. scalar), again for each sample. As a result the output shapes would be (3, 3)
and (3, 1)
.
Update: If you want your network to accept an input sample of shape (3,3)
and outputs vectors of size 3 and 1, and you want to only use Dense layers in your network, then you must use a Flatten
layer somewhere in the model. One possible option is to use it right after the input layer:
inp = layers.Input((3,3)) # don't forget to set the correct input shape
x = Flatten()(inp)
# pass x to other Dense layers
Alternatively, you could flatten your data to have a shape of (num_samples, 9)
and then pass it to your network without using a Flatten
layer.
Update 2: As @Mete correctly pointed out in the comments, make sure the input array have a shape of (num_samples, 3, 3)
if each input sample has a shape of (3,3)
.
edited Nov 21 '18 at 12:33
answered Nov 21 '18 at 12:20
todaytoday
11.3k22239
11.3k22239
I don't want to have in input 3 samples of size 3. I want to have one sample of size 3x3. Could you tell me how to do that?
– Federico Dorato
Nov 21 '18 at 12:22
@FedericoDorato Please see my updated answer.
– today
Nov 21 '18 at 12:28
inp = layers.Input((3,3))
means every sample is 3x3inpu = np.array([[[1,2,3],[4,5,6],[7,8,9]]])
(note shape is 1x3x3) means you have 1 sample of 3x3 data
– Mete Han Kahraman
Nov 21 '18 at 12:29
@FedericoDorato Please see the second update.
– today
Nov 21 '18 at 12:35
@today i am forced to follow this: "Alternatively, you could flatten your data to have a shape of (num_samples, 9) and then pass it to your network without using a Flatten layer." Because otherwise there is this error: 'Tensor' object has no attribute 'lower'
– Federico Dorato
Nov 30 '18 at 15:05
|
show 1 more comment
I don't want to have in input 3 samples of size 3. I want to have one sample of size 3x3. Could you tell me how to do that?
– Federico Dorato
Nov 21 '18 at 12:22
@FedericoDorato Please see my updated answer.
– today
Nov 21 '18 at 12:28
inp = layers.Input((3,3))
means every sample is 3x3inpu = np.array([[[1,2,3],[4,5,6],[7,8,9]]])
(note shape is 1x3x3) means you have 1 sample of 3x3 data
– Mete Han Kahraman
Nov 21 '18 at 12:29
@FedericoDorato Please see the second update.
– today
Nov 21 '18 at 12:35
@today i am forced to follow this: "Alternatively, you could flatten your data to have a shape of (num_samples, 9) and then pass it to your network without using a Flatten layer." Because otherwise there is this error: 'Tensor' object has no attribute 'lower'
– Federico Dorato
Nov 30 '18 at 15:05
I don't want to have in input 3 samples of size 3. I want to have one sample of size 3x3. Could you tell me how to do that?
– Federico Dorato
Nov 21 '18 at 12:22
I don't want to have in input 3 samples of size 3. I want to have one sample of size 3x3. Could you tell me how to do that?
– Federico Dorato
Nov 21 '18 at 12:22
@FedericoDorato Please see my updated answer.
– today
Nov 21 '18 at 12:28
@FedericoDorato Please see my updated answer.
– today
Nov 21 '18 at 12:28
inp = layers.Input((3,3))
means every sample is 3x3 inpu = np.array([[[1,2,3],[4,5,6],[7,8,9]]])
(note shape is 1x3x3) means you have 1 sample of 3x3 data– Mete Han Kahraman
Nov 21 '18 at 12:29
inp = layers.Input((3,3))
means every sample is 3x3 inpu = np.array([[[1,2,3],[4,5,6],[7,8,9]]])
(note shape is 1x3x3) means you have 1 sample of 3x3 data– Mete Han Kahraman
Nov 21 '18 at 12:29
@FedericoDorato Please see the second update.
– today
Nov 21 '18 at 12:35
@FedericoDorato Please see the second update.
– today
Nov 21 '18 at 12:35
@today i am forced to follow this: "Alternatively, you could flatten your data to have a shape of (num_samples, 9) and then pass it to your network without using a Flatten layer." Because otherwise there is this error: 'Tensor' object has no attribute 'lower'
– Federico Dorato
Nov 30 '18 at 15:05
@today i am forced to follow this: "Alternatively, you could flatten your data to have a shape of (num_samples, 9) and then pass it to your network without using a Flatten layer." Because otherwise there is this error: 'Tensor' object has no attribute 'lower'
– Federico Dorato
Nov 30 '18 at 15:05
|
show 1 more 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%2f53411566%2fkeras-input-with-size-xx-generates-unwanted-output-yx%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