Recover tensor after tensor.view in pytorch











up vote
0
down vote

favorite












I have a tensor t of dimension [B, C, H, W]. I used view() to make it two dimensional and dumped it in some file.



tensor.view(B, -1)


Now during file reading, I want to recover the dumped tensor. How to recover that correctly?










share|improve this question




























    up vote
    0
    down vote

    favorite












    I have a tensor t of dimension [B, C, H, W]. I used view() to make it two dimensional and dumped it in some file.



    tensor.view(B, -1)


    Now during file reading, I want to recover the dumped tensor. How to recover that correctly?










    share|improve this question


























      up vote
      0
      down vote

      favorite









      up vote
      0
      down vote

      favorite











      I have a tensor t of dimension [B, C, H, W]. I used view() to make it two dimensional and dumped it in some file.



      tensor.view(B, -1)


      Now during file reading, I want to recover the dumped tensor. How to recover that correctly?










      share|improve this question















      I have a tensor t of dimension [B, C, H, W]. I used view() to make it two dimensional and dumped it in some file.



      tensor.view(B, -1)


      Now during file reading, I want to recover the dumped tensor. How to recover that correctly?







      python-3.x pytorch






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited yesterday

























      asked yesterday









      random_28

      711415




      711415
























          1 Answer
          1






          active

          oldest

          votes

















          up vote
          0
          down vote













          view only changes the sizes of the tensor, while the underlying content remains the same. You can switch that back such as below:



          t=tensor.view(B,-1)
          new_t = t.view(B,H,W,C)





          share|improve this answer























          • The tensor I dump into some file and read from a different program. Although, I do know the initial dimensions.
            – random_28
            yesterday










          • There you go my friend, I would use that solution in order to restore you initial tensor.
            – Jonathan Gagne
            yesterday










          • Can u pls explain what's the need for permute ?
            – random_28
            yesterday










          • Permute switch the dimensions of the tensor to the he desired ordering of dimensions.
            – Jonathan Gagne
            yesterday












          • what if I just do t=tensor.view(B,-1) and then new_t = t.view(B,H,W,C). ?
            – random_28
            yesterday











          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',
          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


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53401620%2frecover-tensor-after-tensor-view-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








          up vote
          0
          down vote













          view only changes the sizes of the tensor, while the underlying content remains the same. You can switch that back such as below:



          t=tensor.view(B,-1)
          new_t = t.view(B,H,W,C)





          share|improve this answer























          • The tensor I dump into some file and read from a different program. Although, I do know the initial dimensions.
            – random_28
            yesterday










          • There you go my friend, I would use that solution in order to restore you initial tensor.
            – Jonathan Gagne
            yesterday










          • Can u pls explain what's the need for permute ?
            – random_28
            yesterday










          • Permute switch the dimensions of the tensor to the he desired ordering of dimensions.
            – Jonathan Gagne
            yesterday












          • what if I just do t=tensor.view(B,-1) and then new_t = t.view(B,H,W,C). ?
            – random_28
            yesterday















          up vote
          0
          down vote













          view only changes the sizes of the tensor, while the underlying content remains the same. You can switch that back such as below:



          t=tensor.view(B,-1)
          new_t = t.view(B,H,W,C)





          share|improve this answer























          • The tensor I dump into some file and read from a different program. Although, I do know the initial dimensions.
            – random_28
            yesterday










          • There you go my friend, I would use that solution in order to restore you initial tensor.
            – Jonathan Gagne
            yesterday










          • Can u pls explain what's the need for permute ?
            – random_28
            yesterday










          • Permute switch the dimensions of the tensor to the he desired ordering of dimensions.
            – Jonathan Gagne
            yesterday












          • what if I just do t=tensor.view(B,-1) and then new_t = t.view(B,H,W,C). ?
            – random_28
            yesterday













          up vote
          0
          down vote










          up vote
          0
          down vote









          view only changes the sizes of the tensor, while the underlying content remains the same. You can switch that back such as below:



          t=tensor.view(B,-1)
          new_t = t.view(B,H,W,C)





          share|improve this answer














          view only changes the sizes of the tensor, while the underlying content remains the same. You can switch that back such as below:



          t=tensor.view(B,-1)
          new_t = t.view(B,H,W,C)






          share|improve this answer














          share|improve this answer



          share|improve this answer








          edited yesterday

























          answered yesterday









          Jonathan Gagne

          1




          1












          • The tensor I dump into some file and read from a different program. Although, I do know the initial dimensions.
            – random_28
            yesterday










          • There you go my friend, I would use that solution in order to restore you initial tensor.
            – Jonathan Gagne
            yesterday










          • Can u pls explain what's the need for permute ?
            – random_28
            yesterday










          • Permute switch the dimensions of the tensor to the he desired ordering of dimensions.
            – Jonathan Gagne
            yesterday












          • what if I just do t=tensor.view(B,-1) and then new_t = t.view(B,H,W,C). ?
            – random_28
            yesterday


















          • The tensor I dump into some file and read from a different program. Although, I do know the initial dimensions.
            – random_28
            yesterday










          • There you go my friend, I would use that solution in order to restore you initial tensor.
            – Jonathan Gagne
            yesterday










          • Can u pls explain what's the need for permute ?
            – random_28
            yesterday










          • Permute switch the dimensions of the tensor to the he desired ordering of dimensions.
            – Jonathan Gagne
            yesterday












          • what if I just do t=tensor.view(B,-1) and then new_t = t.view(B,H,W,C). ?
            – random_28
            yesterday
















          The tensor I dump into some file and read from a different program. Although, I do know the initial dimensions.
          – random_28
          yesterday




          The tensor I dump into some file and read from a different program. Although, I do know the initial dimensions.
          – random_28
          yesterday












          There you go my friend, I would use that solution in order to restore you initial tensor.
          – Jonathan Gagne
          yesterday




          There you go my friend, I would use that solution in order to restore you initial tensor.
          – Jonathan Gagne
          yesterday












          Can u pls explain what's the need for permute ?
          – random_28
          yesterday




          Can u pls explain what's the need for permute ?
          – random_28
          yesterday












          Permute switch the dimensions of the tensor to the he desired ordering of dimensions.
          – Jonathan Gagne
          yesterday






          Permute switch the dimensions of the tensor to the he desired ordering of dimensions.
          – Jonathan Gagne
          yesterday














          what if I just do t=tensor.view(B,-1) and then new_t = t.view(B,H,W,C). ?
          – random_28
          yesterday




          what if I just do t=tensor.view(B,-1) and then new_t = t.view(B,H,W,C). ?
          – random_28
          yesterday


















           

          draft saved


          draft discarded



















































           


          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53401620%2frecover-tensor-after-tensor-view-in-pytorch%23new-answer', 'question_page');
          }
          );

          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







          Popular posts from this blog

          Berounka

          Sphinx de Gizeh

          Different font size/position of beamer's navigation symbols template's content depending on regular/plain...