Resize 5-D Tensor in Tensorflow with trilinear interpolation
I am currently working on a problem where I need to resize a 5-D tensor [batch, length, width, height, num_channels] where lenght, width and height need to be resampled linearly, using ideally a trilinear interpolation. Ideally, I would like to be able to use the tf.image.crop_and_resize function, but this only works for 2-D images, not image volumes. For simplicity, I can let the batch=1, and just loop it through each batch. I know this isn't efficient, but it does work. I would need this for a deeper part of the network, for the num_channels wouldn't be 3 rgb, or 1 for gray-scale, but something like 1024. Ideally, something like skimage.transform.resize for tensorflow would perfect.
python tensorflow
edited Nov 20 at 17:43
Cheche
834218
asked Nov 20 at 16:35
krolic
1
add a comment |
I am currently working on a problem where I need to resize a 5-D tensor [batch, length, width, height, num_channels] where lenght, width and height need to be resampled linearly, using ideally a trilinear interpolation. Ideally, I would like to be able to use the tf.image.crop_and_resize function, but this only works for 2-D images, not image volumes. For simplicity, I can let the batch=1, and just loop it through each batch. I know this isn't efficient, but it does work. I would need this for a deeper part of the network, for the num_channels wouldn't be 3 rgb, or 1 for gray-scale, but something like 1024. Ideally, something like skimage.transform.resize for tensorflow would perfect.
python tensorflow
edited Nov 20 at 17:43
Cheche
834218
asked Nov 20 at 16:35
krolic
1
You could do a bilinear interpolation and then another linear interpolation for the remaining dimension. I'm not sure if there is a linear interpolation op in TensorFlow, but otherwise it should be easy to write, and in any case you can use a second image resize leaving one dimension untouched.
– jdehesa
Nov 20 at 17:53
add a comment |
I am currently working on a problem where I need to resize a 5-D tensor [batch, length, width, height, num_channels] where lenght, width and height need to be resampled linearly, using ideally a trilinear interpolation. Ideally, I would like to be able to use the tf.image.crop_and_resize function, but this only works for 2-D images, not image volumes. For simplicity, I can let the batch=1, and just loop it through each batch. I know this isn't efficient, but it does work. I would need this for a deeper part of the network, for the num_channels wouldn't be 3 rgb, or 1 for gray-scale, but something like 1024. Ideally, something like skimage.transform.resize for tensorflow would perfect.
python tensorflow
edited Nov 20 at 17:43
Cheche
834218
asked Nov 20 at 16:35
krolic
1
I am currently working on a problem where I need to resize a 5-D tensor [batch, length, width, height, num_channels] where lenght, width and height need to be resampled linearly, using ideally a trilinear interpolation. Ideally, I would like to be able to use the tf.image.crop_and_resize function, but this only works for 2-D images, not image volumes. For simplicity, I can let the batch=1, and just loop it through each batch. I know this isn't efficient, but it does work. I would need this for a deeper part of the network, for the num_channels wouldn't be 3 rgb, or 1 for gray-scale, but something like 1024. Ideally, something like skimage.transform.resize for tensorflow would perfect.
python tensorflow
python tensorflow
edited Nov 20 at 17:43
Cheche
834218
asked Nov 20 at 16:35
krolic
1
edited Nov 20 at 17:43
Cheche
834218
asked Nov 20 at 16:35
krolic
1
edited Nov 20 at 17:43
Cheche
834218
edited Nov 20 at 17:43
Cheche
834218
edited Nov 20 at 17:43
Cheche
834218
834218
asked Nov 20 at 16:35
krolic
1
asked Nov 20 at 16:35
krolic
1
asked Nov 20 at 16:35
krolic
1
1
You could do a bilinear interpolation and then another linear interpolation for the remaining dimension. I'm not sure if there is a linear interpolation op in TensorFlow, but otherwise it should be easy to write, and in any case you can use a second image resize leaving one dimension untouched.
– jdehesa
Nov 20 at 17:53
add a comment |
You could do a bilinear interpolation and then another linear interpolation for the remaining dimension. I'm not sure if there is a linear interpolation op in TensorFlow, but otherwise it should be easy to write, and in any case you can use a second image resize leaving one dimension untouched.
– jdehesa
Nov 20 at 17:53
You could do a bilinear interpolation and then another linear interpolation for the remaining dimension. I'm not sure if there is a linear interpolation op in TensorFlow, but otherwise it should be easy to write, and in any case you can use a second image resize leaving one dimension untouched.
– jdehesa
Nov 20 at 17:53
You could do a bilinear interpolation and then another linear interpolation for the remaining dimension. I'm not sure if there is a linear interpolation op in TensorFlow, but otherwise it should be easy to write, and in any case you can use a second image resize leaving one dimension untouched.
– jdehesa
Nov 20 at 17:53
add a comment |
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%2f53397505%2fresize-5-d-tensor-in-tensorflow-with-trilinear-interpolation%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
active
oldest
votes
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.
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%2f53397505%2fresize-5-d-tensor-in-tensorflow-with-trilinear-interpolation%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
You could do a bilinear interpolation and then another linear interpolation for the remaining dimension. I'm not sure if there is a linear interpolation op in TensorFlow, but otherwise it should be easy to write, and in any case you can use a second image resize leaving one dimension untouched.
– jdehesa
Nov 20 at 17:53