In Tensorflow, how to reconstruct tensors with the same label?
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ height:90px;width:728px;box-sizing:border-box;
}
I want to implement a function that reconstructs tensors with the same label. For example, we have a tensor feature BxNxC and its label BxN, B is batch size, C is the dimension of features, the range of label is K, the output I want is BxKxC. Features with the same label are combined together and outputs its mean feature with its specific label。
Anyone know how to implement this function?
I have implemented some but it seems ugly.
label_class = 12
for batch in range(part_pred.get_shape().as_list()[0]):
batch_label = part_label[batch]
batch_pred = mesh_point_net[batch,...]
for label in range(label_class):
condition = tf.equal(batch_label, label)
index = tf.where(condition)
pred = tf.reduce_mean(tf.gather(batch_pred, index), axis=0)
if label == 0:
batch_mean_pred = pred
else:
batch_mean_pred = tf.concat([batch_mean_pred, pred], axis=0)
if batch == 0:
mean_pred = tf.expand_dims(batch_mean_pred, axis=0)
else:
mean_pred = tf.concat([mean_pred,tf.expand_dims(batch_mean_pred, axis=0)], axis=0)
python tensorflow
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
add a comment |
I want to implement a function that reconstructs tensors with the same label. For example, we have a tensor feature BxNxC and its label BxN, B is batch size, C is the dimension of features, the range of label is K, the output I want is BxKxC. Features with the same label are combined together and outputs its mean feature with its specific label。
Anyone know how to implement this function?
I have implemented some but it seems ugly.
label_class = 12
for batch in range(part_pred.get_shape().as_list()[0]):
batch_label = part_label[batch]
batch_pred = mesh_point_net[batch,...]
for label in range(label_class):
condition = tf.equal(batch_label, label)
index = tf.where(condition)
pred = tf.reduce_mean(tf.gather(batch_pred, index), axis=0)
if label == 0:
batch_mean_pred = pred
else:
batch_mean_pred = tf.concat([batch_mean_pred, pred], axis=0)
if batch == 0:
mean_pred = tf.expand_dims(batch_mean_pred, axis=0)
else:
mean_pred = tf.concat([mean_pred,tf.expand_dims(batch_mean_pred, axis=0)], axis=0)
python tensorflow
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
Or which function can implement batch operations?
– Xu Zhengtian
Nov 17 '18 at 10:48
add a comment |
I want to implement a function that reconstructs tensors with the same label. For example, we have a tensor feature BxNxC and its label BxN, B is batch size, C is the dimension of features, the range of label is K, the output I want is BxKxC. Features with the same label are combined together and outputs its mean feature with its specific label。
Anyone know how to implement this function?
I have implemented some but it seems ugly.
label_class = 12
for batch in range(part_pred.get_shape().as_list()[0]):
batch_label = part_label[batch]
batch_pred = mesh_point_net[batch,...]
for label in range(label_class):
condition = tf.equal(batch_label, label)
index = tf.where(condition)
pred = tf.reduce_mean(tf.gather(batch_pred, index), axis=0)
if label == 0:
batch_mean_pred = pred
else:
batch_mean_pred = tf.concat([batch_mean_pred, pred], axis=0)
if batch == 0:
mean_pred = tf.expand_dims(batch_mean_pred, axis=0)
else:
mean_pred = tf.concat([mean_pred,tf.expand_dims(batch_mean_pred, axis=0)], axis=0)
python tensorflow
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
I want to implement a function that reconstructs tensors with the same label. For example, we have a tensor feature BxNxC and its label BxN, B is batch size, C is the dimension of features, the range of label is K, the output I want is BxKxC. Features with the same label are combined together and outputs its mean feature with its specific label。
Anyone know how to implement this function?
I have implemented some but it seems ugly.
label_class = 12
for batch in range(part_pred.get_shape().as_list()[0]):
batch_label = part_label[batch]
batch_pred = mesh_point_net[batch,...]
for label in range(label_class):
condition = tf.equal(batch_label, label)
index = tf.where(condition)
pred = tf.reduce_mean(tf.gather(batch_pred, index), axis=0)
if label == 0:
batch_mean_pred = pred
else:
batch_mean_pred = tf.concat([batch_mean_pred, pred], axis=0)
if batch == 0:
mean_pred = tf.expand_dims(batch_mean_pred, axis=0)
else:
mean_pred = tf.concat([mean_pred,tf.expand_dims(batch_mean_pred, axis=0)], axis=0)
python tensorflow
python tensorflow
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
asked Nov 16 '18 at 17:41
Xu ZhengtianXu Zhengtian
111
111
Or which function can implement batch operations?
– Xu Zhengtian
Nov 17 '18 at 10:48
add a comment |
Or which function can implement batch operations?
– Xu Zhengtian
Nov 17 '18 at 10:48
Or which function can implement batch operations?
– Xu Zhengtian
Nov 17 '18 at 10:48
Or which function can implement batch operations?
– Xu Zhengtian
Nov 17 '18 at 10:48
add a comment |
0
active
oldest
votes
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%2f53342867%2fin-tensorflow-how-to-reconstruct-tensors-with-the-same-label%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%2f53342867%2fin-tensorflow-how-to-reconstruct-tensors-with-the-same-label%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
Or which function can implement batch operations?
– Xu Zhengtian
Nov 17 '18 at 10:48