Map function to partial tensor in TensorFlow
In the TensorFlow architecture, how do you apply a function to only some elements in a tensor? For example, on the final output of a layer, some variables represent pixel densities which I would like to run through a sigmoid, and a few variables at the beginning of the tensor represent unbounded continuous values, which I would not like to apply an activation function at all.
Here is what I am trying:
output_activation=tf.nn.sigmoid
x = tf.layers.dense(z, hidden_size, activation=hidden_activation)
x = tf.layers.dense(x, hidden_size, activation=hidden_activation)
_logits = tf.layers.dense(x, output_size, activation=None)
# Apply sigmoid only to image variables
logits = tf.concat(_logits[:functional_inputs], tf.map_fn(output_activation, _logits[functional_inputs:]), 0)
Which is giving the following value error:
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("build_decoder/map/TensorArrayStack/TensorArrayGatherV3:0", shape=(?, 288755), dtype=float32)'
Is this the best way to do this?
python tensorflow
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
add a comment |
In the TensorFlow architecture, how do you apply a function to only some elements in a tensor? For example, on the final output of a layer, some variables represent pixel densities which I would like to run through a sigmoid, and a few variables at the beginning of the tensor represent unbounded continuous values, which I would not like to apply an activation function at all.
Here is what I am trying:
output_activation=tf.nn.sigmoid
x = tf.layers.dense(z, hidden_size, activation=hidden_activation)
x = tf.layers.dense(x, hidden_size, activation=hidden_activation)
_logits = tf.layers.dense(x, output_size, activation=None)
# Apply sigmoid only to image variables
logits = tf.concat(_logits[:functional_inputs], tf.map_fn(output_activation, _logits[functional_inputs:]), 0)
Which is giving the following value error:
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("build_decoder/map/TensorArrayStack/TensorArrayGatherV3:0", shape=(?, 288755), dtype=float32)'
Is this the best way to do this?
python tensorflow
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
I think the problem is inoutput_activation, which seems to return aint32tensor for thefloat32input. From the documentation oftf.map_fn: "Users must providedtypeif it is different from the data type ofelems". So try addingdtype=tf.int32totf.map_fn.
– jdehesa
Nov 29 '18 at 10:32
I will give that a shot, thanks
– taylormade201
Nov 29 '18 at 23:02
add a comment |
In the TensorFlow architecture, how do you apply a function to only some elements in a tensor? For example, on the final output of a layer, some variables represent pixel densities which I would like to run through a sigmoid, and a few variables at the beginning of the tensor represent unbounded continuous values, which I would not like to apply an activation function at all.
Here is what I am trying:
output_activation=tf.nn.sigmoid
x = tf.layers.dense(z, hidden_size, activation=hidden_activation)
x = tf.layers.dense(x, hidden_size, activation=hidden_activation)
_logits = tf.layers.dense(x, output_size, activation=None)
# Apply sigmoid only to image variables
logits = tf.concat(_logits[:functional_inputs], tf.map_fn(output_activation, _logits[functional_inputs:]), 0)
Which is giving the following value error:
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("build_decoder/map/TensorArrayStack/TensorArrayGatherV3:0", shape=(?, 288755), dtype=float32)'
Is this the best way to do this?
python tensorflow
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
In the TensorFlow architecture, how do you apply a function to only some elements in a tensor? For example, on the final output of a layer, some variables represent pixel densities which I would like to run through a sigmoid, and a few variables at the beginning of the tensor represent unbounded continuous values, which I would not like to apply an activation function at all.
Here is what I am trying:
output_activation=tf.nn.sigmoid
x = tf.layers.dense(z, hidden_size, activation=hidden_activation)
x = tf.layers.dense(x, hidden_size, activation=hidden_activation)
_logits = tf.layers.dense(x, output_size, activation=None)
# Apply sigmoid only to image variables
logits = tf.concat(_logits[:functional_inputs], tf.map_fn(output_activation, _logits[functional_inputs:]), 0)
Which is giving the following value error:
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("build_decoder/map/TensorArrayStack/TensorArrayGatherV3:0", shape=(?, 288755), dtype=float32)'
Is this the best way to do this?
python tensorflow
python tensorflow
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
asked Nov 28 '18 at 22:18
taylormade201taylormade201
2711620
2711620
I think the problem is inoutput_activation, which seems to return aint32tensor for thefloat32input. From the documentation oftf.map_fn: "Users must providedtypeif it is different from the data type ofelems". So try addingdtype=tf.int32totf.map_fn.
– jdehesa
Nov 29 '18 at 10:32
I will give that a shot, thanks
– taylormade201
Nov 29 '18 at 23:02
add a comment |
I think the problem is inoutput_activation, which seems to return aint32tensor for thefloat32input. From the documentation oftf.map_fn: "Users must providedtypeif it is different from the data type ofelems". So try addingdtype=tf.int32totf.map_fn.
– jdehesa
Nov 29 '18 at 10:32
I will give that a shot, thanks
– taylormade201
Nov 29 '18 at 23:02
I think the problem is in
output_activation, which seems to return a int32 tensor for the float32 input. From the documentation of tf.map_fn: "Users must provide dtype if it is different from the data type of elems". So try adding dtype=tf.int32 to tf.map_fn.– jdehesa
Nov 29 '18 at 10:32
I think the problem is in
output_activation, which seems to return a int32 tensor for the float32 input. From the documentation of tf.map_fn: "Users must provide dtype if it is different from the data type of elems". So try adding dtype=tf.int32 to tf.map_fn.– jdehesa
Nov 29 '18 at 10:32
I will give that a shot, thanks
– taylormade201
Nov 29 '18 at 23:02
I will give that a shot, thanks
– taylormade201
Nov 29 '18 at 23:02
add a comment |
0
active
oldest
votes
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%2f53528950%2fmap-function-to-partial-tensor-in-tensorflow%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%2f53528950%2fmap-function-to-partial-tensor-in-tensorflow%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
I think the problem is in
output_activation, which seems to return aint32tensor for thefloat32input. From the documentation oftf.map_fn: "Users must providedtypeif it is different from the data type ofelems". So try addingdtype=tf.int32totf.map_fn.– jdehesa
Nov 29 '18 at 10:32
I will give that a shot, thanks
– taylormade201
Nov 29 '18 at 23:02