Update values in tensor along deeper dimensions
I have tensor A of shape MxNxC where M stands for number of examples, N is number of features and C is 3 euler rotation angles. Also i have a tensor B of similar shape, but instead of angles there are coordinates.
What is needed is to convert both of these tensors to one containing affine transformation matrices so its shape would be like MxNx4x4. I dont know how to iterate over these tensors together, I've looked for tf.map_fn and tf.scan but they iterate only with the first dimension. What im looking for is some method to apply function like the one below to all of the elements along the last axes.
def f(angles, vector): #dimensions 3 or 3x1
...
return matrix # dimension 4x4
Any help would be useful, thanks!
python tensorflow tensor
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
add a comment |
I have tensor A of shape MxNxC where M stands for number of examples, N is number of features and C is 3 euler rotation angles. Also i have a tensor B of similar shape, but instead of angles there are coordinates.
What is needed is to convert both of these tensors to one containing affine transformation matrices so its shape would be like MxNx4x4. I dont know how to iterate over these tensors together, I've looked for tf.map_fn and tf.scan but they iterate only with the first dimension. What im looking for is some method to apply function like the one below to all of the elements along the last axes.
def f(angles, vector): #dimensions 3 or 3x1
...
return matrix # dimension 4x4
Any help would be useful, thanks!
python tensorflow tensor
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
add a comment |
I have tensor A of shape MxNxC where M stands for number of examples, N is number of features and C is 3 euler rotation angles. Also i have a tensor B of similar shape, but instead of angles there are coordinates.
What is needed is to convert both of these tensors to one containing affine transformation matrices so its shape would be like MxNx4x4. I dont know how to iterate over these tensors together, I've looked for tf.map_fn and tf.scan but they iterate only with the first dimension. What im looking for is some method to apply function like the one below to all of the elements along the last axes.
def f(angles, vector): #dimensions 3 or 3x1
...
return matrix # dimension 4x4
Any help would be useful, thanks!
python tensorflow tensor
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
I have tensor A of shape MxNxC where M stands for number of examples, N is number of features and C is 3 euler rotation angles. Also i have a tensor B of similar shape, but instead of angles there are coordinates.
What is needed is to convert both of these tensors to one containing affine transformation matrices so its shape would be like MxNx4x4. I dont know how to iterate over these tensors together, I've looked for tf.map_fn and tf.scan but they iterate only with the first dimension. What im looking for is some method to apply function like the one below to all of the elements along the last axes.
def f(angles, vector): #dimensions 3 or 3x1
...
return matrix # dimension 4x4
Any help would be useful, thanks!
python tensorflow tensor
python tensorflow tensor
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
asked Nov 23 '18 at 12:13
mcstarionimcstarioni
166
166
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
you can try something like this:
A_flattened = tf.reshape(A, [-1, 3])# flatten it out
B_flattened = tf.reshape(B, [-1, 3])
AB_flattened = tf.map_fn(convert_to_mat, (A_flattened, B_flattened))# convert_to_mat should return a 4x4 matrix
AB = tf.reshape(AB_flattened, [M, N, 4, 4])
this should do the trick!
answered Nov 23 '18 at 14:33
hampihampi
1164
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%2f53446532%2fupdate-values-in-tensor-along-deeper-dimensions%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 can try something like this:
A_flattened = tf.reshape(A, [-1, 3])# flatten it out
B_flattened = tf.reshape(B, [-1, 3])
AB_flattened = tf.map_fn(convert_to_mat, (A_flattened, B_flattened))# convert_to_mat should return a 4x4 matrix
AB = tf.reshape(AB_flattened, [M, N, 4, 4])
this should do the trick!
answered Nov 23 '18 at 14:33
hampihampi
1164
add a comment |
you can try something like this:
A_flattened = tf.reshape(A, [-1, 3])# flatten it out
B_flattened = tf.reshape(B, [-1, 3])
AB_flattened = tf.map_fn(convert_to_mat, (A_flattened, B_flattened))# convert_to_mat should return a 4x4 matrix
AB = tf.reshape(AB_flattened, [M, N, 4, 4])
this should do the trick!
answered Nov 23 '18 at 14:33
hampihampi
1164
add a comment |
you can try something like this:
A_flattened = tf.reshape(A, [-1, 3])# flatten it out
B_flattened = tf.reshape(B, [-1, 3])
AB_flattened = tf.map_fn(convert_to_mat, (A_flattened, B_flattened))# convert_to_mat should return a 4x4 matrix
AB = tf.reshape(AB_flattened, [M, N, 4, 4])
this should do the trick!
answered Nov 23 '18 at 14:33
hampihampi
1164
you can try something like this:
A_flattened = tf.reshape(A, [-1, 3])# flatten it out
B_flattened = tf.reshape(B, [-1, 3])
AB_flattened = tf.map_fn(convert_to_mat, (A_flattened, B_flattened))# convert_to_mat should return a 4x4 matrix
AB = tf.reshape(AB_flattened, [M, N, 4, 4])
this should do the trick!
answered Nov 23 '18 at 14:33
hampihampi
1164
answered Nov 23 '18 at 14:33
hampihampi
1164
answered Nov 23 '18 at 14:33
hampihampi
1164
answered Nov 23 '18 at 14:33
hampihampi
1164
1164
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.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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%2f53446532%2fupdate-values-in-tensor-along-deeper-dimensions%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
