Mixing
Keras Error when Concatenating layers in functional mode
I'm attempting to concatenate two layers. According to the documentation, the following should be correct.
import tensorflow.keras as K
input = K.Input(shape=(self.state_dimensions(),))
shared_features = K.layers.Dense(10,activation='tanh')
x = K.layers.Dense(10, activation='tanh')(input)
a = shared_features(x[0:10])
b = shared_features(x[10:20])
output = K.layers.Concatenate()([a,b])
actor_model = K.Model(inputs=input, outputs=output)
However, in the last line, this error appears:
ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)
tensorflow keras
asked Jan 2 at 15:58
gufftangufftan
88312
add a comment |
I'm attempting to concatenate two layers. According to the documentation, the following should be correct.
import tensorflow.keras as K
input = K.Input(shape=(self.state_dimensions(),))
shared_features = K.layers.Dense(10,activation='tanh')
x = K.layers.Dense(10, activation='tanh')(input)
a = shared_features(x[0:10])
b = shared_features(x[10:20])
output = K.layers.Concatenate()([a,b])
actor_model = K.Model(inputs=input, outputs=output)
However, in the last line, this error appears:
ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)
tensorflow keras
asked Jan 2 at 15:58
gufftangufftan
88312
add a comment |
I'm attempting to concatenate two layers. According to the documentation, the following should be correct.
import tensorflow.keras as K
input = K.Input(shape=(self.state_dimensions(),))
shared_features = K.layers.Dense(10,activation='tanh')
x = K.layers.Dense(10, activation='tanh')(input)
a = shared_features(x[0:10])
b = shared_features(x[10:20])
output = K.layers.Concatenate()([a,b])
actor_model = K.Model(inputs=input, outputs=output)
However, in the last line, this error appears:
ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)
tensorflow keras
asked Jan 2 at 15:58
gufftangufftan
88312
I'm attempting to concatenate two layers. According to the documentation, the following should be correct.
import tensorflow.keras as K
input = K.Input(shape=(self.state_dimensions(),))
shared_features = K.layers.Dense(10,activation='tanh')
x = K.layers.Dense(10, activation='tanh')(input)
a = shared_features(x[0:10])
b = shared_features(x[10:20])
output = K.layers.Concatenate()([a,b])
actor_model = K.Model(inputs=input, outputs=output)
However, in the last line, this error appears:
ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)
tensorflow keras
tensorflow keras
asked Jan 2 at 15:58
gufftangufftan
88312
asked Jan 2 at 15:58
gufftangufftan
88312
asked Jan 2 at 15:58
gufftangufftan
88312
asked Jan 2 at 15:58
gufftangufftan
88312
asked Jan 2 at 15:58
gufftangufftan
88312
88312
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
Tensors a and b contain operations outside layers. All operations must be inside keras layers.
a = K.layers.Lambda(lambda x: x[:10])(x)
b = K.layers.Lambda(lambda x: x[10:20])(x)
a = shared_features(a)
b = shared_features(b)
You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.
You probably want x[:,0:10] and x[:,10:20]
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
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%2f54009380%2fkeras-error-when-concatenating-layers-in-functional-mode%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
Tensors a and b contain operations outside layers. All operations must be inside keras layers.
a = K.layers.Lambda(lambda x: x[:10])(x)
b = K.layers.Lambda(lambda x: x[10:20])(x)
a = shared_features(a)
b = shared_features(b)
You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.
You probably want x[:,0:10] and x[:,10:20]
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
add a comment |
Tensors a and b contain operations outside layers. All operations must be inside keras layers.
a = K.layers.Lambda(lambda x: x[:10])(x)
b = K.layers.Lambda(lambda x: x[10:20])(x)
a = shared_features(a)
b = shared_features(b)
You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.
You probably want x[:,0:10] and x[:,10:20]
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
add a comment |
Tensors a and b contain operations outside layers. All operations must be inside keras layers.
a = K.layers.Lambda(lambda x: x[:10])(x)
b = K.layers.Lambda(lambda x: x[10:20])(x)
a = shared_features(a)
b = shared_features(b)
You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.
You probably want x[:,0:10] and x[:,10:20]
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
Tensors a and b contain operations outside layers. All operations must be inside keras layers.
a = K.layers.Lambda(lambda x: x[:10])(x)
b = K.layers.Lambda(lambda x: x[10:20])(x)
a = shared_features(a)
b = shared_features(b)
You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.
You probably want x[:,0:10] and x[:,10:20]
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
answered Jan 2 at 16:10
Daniel MöllerDaniel Möller
37.6k671108
37.6k671108
add a comment |
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%2f54009380%2fkeras-error-when-concatenating-layers-in-functional-mode%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
