How to convert 3D tensor to 2D tensor in pytorch?
0
I am new to pytorch. I have 3D tensor (32,10,64) and I want a 2D tensor (32, 64).
I tried view() and used after passing to linear layer squeeze() which converted it to (32,10).
python deep-learning pytorch
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
asked Nov 26 '18 at 2:32
amyamy
978
add a comment |
0
I am new to pytorch. I have 3D tensor (32,10,64) and I want a 2D tensor (32, 64).
I tried view() and used after passing to linear layer squeeze() which converted it to (32,10).
python deep-learning pytorch
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
asked Nov 26 '18 at 2:32
amyamy
978
1
in what way does the output relate to the input int this case? you have x10 more inputs that outputs. Do you want to sample from the input? do you want to combine the inputs to form the output? you need to be more specific...
– Shai
Nov 27 '18 at 12:43
add a comment |
0
0
0
I am new to pytorch. I have 3D tensor (32,10,64) and I want a 2D tensor (32, 64).
I tried view() and used after passing to linear layer squeeze() which converted it to (32,10).
python deep-learning pytorch
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
asked Nov 26 '18 at 2:32
amyamy
978
I am new to pytorch. I have 3D tensor (32,10,64) and I want a 2D tensor (32, 64).
I tried view() and used after passing to linear layer squeeze() which converted it to (32,10).
python deep-learning pytorch
python deep-learning pytorch
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
asked Nov 26 '18 at 2:32
amyamy
978
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
asked Nov 26 '18 at 2:32
amyamy
978
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
edited Nov 27 '18 at 12:22
Anubhav Singh
1431212
1431212
asked Nov 26 '18 at 2:32
amyamy
978
asked Nov 26 '18 at 2:32
amyamy
978
asked Nov 26 '18 at 2:32
amyamy
978
978
1
in what way does the output relate to the input int this case? you have x10 more inputs that outputs. Do you want to sample from the input? do you want to combine the inputs to form the output? you need to be more specific...
– Shai
Nov 27 '18 at 12:43
add a comment |
1
in what way does the output relate to the input int this case? you have x10 more inputs that outputs. Do you want to sample from the input? do you want to combine the inputs to form the output? you need to be more specific...
– Shai
Nov 27 '18 at 12:43
1
1
in what way does the output relate to the input int this case? you have x10 more inputs that outputs. Do you want to sample from the input? do you want to combine the inputs to form the output? you need to be more specific...
– Shai
Nov 27 '18 at 12:43
in what way does the output relate to the input int this case? you have x10 more inputs that outputs. Do you want to sample from the input? do you want to combine the inputs to form the output? you need to be more specific...
– Shai
Nov 27 '18 at 12:43
add a comment |
1 Answer
1
active
oldest
votes
2
Try this
t = torch.rand(32, 10, 64).permute(0, 2, 1)[:, :, -1]
or, as pointed out by Shai, you could also
t = torch.rand(32, 10, 64)[:, -1, :]
print(t.size()) # torch.Size([32, 64])
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
1
whypermute()?? how is it different from simplyt[:, -1, :]?
– Shai
Nov 27 '18 at 12:40
1
@Shai You can do that as well, its more straightforward :)
– Rex Low
Nov 27 '18 at 13:23
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
});
}
});
draft saved
draft discarded
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%2f53474056%2fhow-to-convert-3d-tensor-to-2d-tensor-in-pytorch%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
2
Try this
t = torch.rand(32, 10, 64).permute(0, 2, 1)[:, :, -1]
or, as pointed out by Shai, you could also
t = torch.rand(32, 10, 64)[:, -1, :]
print(t.size()) # torch.Size([32, 64])
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
1
whypermute()?? how is it different from simplyt[:, -1, :]?
– Shai
Nov 27 '18 at 12:40
1
@Shai You can do that as well, its more straightforward :)
– Rex Low
Nov 27 '18 at 13:23
add a comment |
2
Try this
t = torch.rand(32, 10, 64).permute(0, 2, 1)[:, :, -1]
or, as pointed out by Shai, you could also
t = torch.rand(32, 10, 64)[:, -1, :]
print(t.size()) # torch.Size([32, 64])
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
1
whypermute()?? how is it different from simplyt[:, -1, :]?
– Shai
Nov 27 '18 at 12:40
1
@Shai You can do that as well, its more straightforward :)
– Rex Low
Nov 27 '18 at 13:23
add a comment |
2
2
2
Try this
t = torch.rand(32, 10, 64).permute(0, 2, 1)[:, :, -1]
or, as pointed out by Shai, you could also
t = torch.rand(32, 10, 64)[:, -1, :]
print(t.size()) # torch.Size([32, 64])
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
Try this
t = torch.rand(32, 10, 64).permute(0, 2, 1)[:, :, -1]
or, as pointed out by Shai, you could also
t = torch.rand(32, 10, 64)[:, -1, :]
print(t.size()) # torch.Size([32, 64])
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
edited Nov 27 '18 at 14:09
Shai
70.4k23137247
70.4k23137247
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
answered Nov 26 '18 at 5:14
Rex LowRex Low
9301824
9301824
1
whypermute()?? how is it different from simplyt[:, -1, :]?
– Shai
Nov 27 '18 at 12:40
1
@Shai You can do that as well, its more straightforward :)
– Rex Low
Nov 27 '18 at 13:23
add a comment |
1
whypermute()?? how is it different from simplyt[:, -1, :]?
– Shai
Nov 27 '18 at 12:40
1
@Shai You can do that as well, its more straightforward :)
– Rex Low
Nov 27 '18 at 13:23
1
1
why
permute()?? how is it different from simply t[:, -1, :]?– Shai
Nov 27 '18 at 12:40
why
permute()?? how is it different from simply t[:, -1, :]?– Shai
Nov 27 '18 at 12:40
1
1
@Shai You can do that as well, its more straightforward :)
– Rex Low
Nov 27 '18 at 13:23
@Shai You can do that as well, its more straightforward :)
– Rex Low
Nov 27 '18 at 13:23
add a comment |
draft saved
draft discarded
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.
draft saved
draft discarded
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%2f53474056%2fhow-to-convert-3d-tensor-to-2d-tensor-in-pytorch%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
1
in what way does the output relate to the input int this case? you have x10 more inputs that outputs. Do you want to sample from the input? do you want to combine the inputs to form the output? you need to be more specific...
– Shai
Nov 27 '18 at 12:43