Convolution2D gives wrong output shape in Keras





.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ height:90px;width:728px;box-sizing:border-box;
}







0















I'm following tutorial from here and have stuck with simple model creation



model = Sequential()

model.add(Convolution2D(32, kernel_size=(3, 3), activation='relu', input_shape=(1, 28, 28)))

model.output_shape


This should give (None, 32, 26, 26) output but instead I get (None, -1, 26, 32). I guess something wrong with parameters provided or I need to make additional reshape. Maybe something has been changed for Convolution2D and Conv2D in Keras? I'm running 2.2.4 with Theano backend






python machine-learning keras theano convolution







share|improve this question

























  • I get InvalidArgumentError with your code.

    – Tzomas
    Nov 16 '18 at 12:13











  • @Tzomas check keras version you are running, probably you have old one

    – Most Wanted
    Nov 16 '18 at 15:04


















0















I'm following tutorial from here and have stuck with simple model creation



model = Sequential()

model.add(Convolution2D(32, kernel_size=(3, 3), activation='relu', input_shape=(1, 28, 28)))

model.output_shape


This should give (None, 32, 26, 26) output but instead I get (None, -1, 26, 32). I guess something wrong with parameters provided or I need to make additional reshape. Maybe something has been changed for Convolution2D and Conv2D in Keras? I'm running 2.2.4 with Theano backend






python machine-learning keras theano convolution







share|improve this question

























  • I get InvalidArgumentError with your code.

    – Tzomas
    Nov 16 '18 at 12:13











  • @Tzomas check keras version you are running, probably you have old one

    – Most Wanted
    Nov 16 '18 at 15:04














0












0








0








I'm following tutorial from here and have stuck with simple model creation



model = Sequential()

model.add(Convolution2D(32, kernel_size=(3, 3), activation='relu', input_shape=(1, 28, 28)))

model.output_shape


This should give (None, 32, 26, 26) output but instead I get (None, -1, 26, 32). I guess something wrong with parameters provided or I need to make additional reshape. Maybe something has been changed for Convolution2D and Conv2D in Keras? I'm running 2.2.4 with Theano backend






python machine-learning keras theano convolution







share|improve this question
















I'm following tutorial from here and have stuck with simple model creation



model = Sequential()

model.add(Convolution2D(32, kernel_size=(3, 3), activation='relu', input_shape=(1, 28, 28)))

model.output_shape


This should give (None, 32, 26, 26) output but instead I get (None, -1, 26, 32). I guess something wrong with parameters provided or I need to make additional reshape. Maybe something has been changed for Convolution2D and Conv2D in Keras? I'm running 2.2.4 with Theano backend






python machine-learning keras theano convolution




python machine-learning keras theano convolution






share|improve this question















share|improve this question













share|improve this question




share|improve this question








edited Nov 16 '18 at 12:09









Mihai Alexandru-Ionut

30.7k64375




30.7k64375










asked Nov 16 '18 at 12:06









Most WantedMost Wanted

1,14721733




1,14721733













  • I get InvalidArgumentError with your code.

    – Tzomas
    Nov 16 '18 at 12:13











  • @Tzomas check keras version you are running, probably you have old one

    – Most Wanted
    Nov 16 '18 at 15:04



















  • I get InvalidArgumentError with your code.

    – Tzomas
    Nov 16 '18 at 12:13











  • @Tzomas check keras version you are running, probably you have old one

    – Most Wanted
    Nov 16 '18 at 15:04

















I get InvalidArgumentError with your code.

– Tzomas
Nov 16 '18 at 12:13





I get InvalidArgumentError with your code.

– Tzomas
Nov 16 '18 at 12:13













@Tzomas check keras version you are running, probably you have old one

– Most Wanted
Nov 16 '18 at 15:04





@Tzomas check keras version you are running, probably you have old one

– Most Wanted
Nov 16 '18 at 15:04












3 Answers
3






active

oldest

votes


















1














It seems that the channels are in the first axis of input data. Therefore, you need to set data_format argument to "channels_first":



model = Sequential()

model.add(Convolution2D(32, kernel_size=(3, 3),

                        data_format='channels_first',

                        activation='relu', input_shape=(1, 28, 28)))

model.output_shape


Which gives:



(None, 32, 26, 26)





share|improve this answer
























  • perfect, works like a charm

    – Most Wanted
    Nov 16 '18 at 15:03



















0














The problem is that it uses Theano as a backend and probably you are using tensorflow (you should check your setting once again). You can change it with: 



import os

os.environ['KERAS_BACKEND'] = 'theano'


This should be done before importing keras






share|improve this answer































    0














    Well like I wrote in my comment. I got a error with your code. So see that it looks like you have bad shape on input, if you change to input_shape=(28,28,1) then output_shape returns (None, 26, 26, 32)



    I don't know if this is what you are exactly looking for.






    share|improve this answer
























      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


















      StackExchange.ready(
      function () {
      StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53337586%2fconvolution2d-gives-wrong-output-shape-in-keras%23new-answer', 'question_page');
      }
      );

      Post as a guest















      Required, but never shown

























      3 Answers
      3






      active

      oldest

      votes








      3 Answers
      3






      active

      oldest

      votes









      active

      oldest

      votes






      active

      oldest

      votes









      1














      It seems that the channels are in the first axis of input data. Therefore, you need to set data_format argument to "channels_first":



      model = Sequential()
      
model.add(Convolution2D(32, kernel_size=(3, 3),
      
                        data_format='channels_first',
      
                        activation='relu', input_shape=(1, 28, 28)))
      
model.output_shape


      Which gives:



      (None, 32, 26, 26)





      share|improve this answer
























      • perfect, works like a charm

        – Most Wanted
        Nov 16 '18 at 15:03
















      1














      It seems that the channels are in the first axis of input data. Therefore, you need to set data_format argument to "channels_first":



      model = Sequential()
      
model.add(Convolution2D(32, kernel_size=(3, 3),
      
                        data_format='channels_first',
      
                        activation='relu', input_shape=(1, 28, 28)))
      
model.output_shape


      Which gives:



      (None, 32, 26, 26)





      share|improve this answer
























      • perfect, works like a charm

        – Most Wanted
        Nov 16 '18 at 15:03














      1












      1








      1







      It seems that the channels are in the first axis of input data. Therefore, you need to set data_format argument to "channels_first":



      model = Sequential()
      
model.add(Convolution2D(32, kernel_size=(3, 3),
      
                        data_format='channels_first',
      
                        activation='relu', input_shape=(1, 28, 28)))
      
model.output_shape


      Which gives:



      (None, 32, 26, 26)





      share|improve this answer













      It seems that the channels are in the first axis of input data. Therefore, you need to set data_format argument to "channels_first":



      model = Sequential()
      
model.add(Convolution2D(32, kernel_size=(3, 3),
      
                        data_format='channels_first',
      
                        activation='relu', input_shape=(1, 28, 28)))
      
model.output_shape


      Which gives:



      (None, 32, 26, 26)






      share|improve this answer












      share|improve this answer



      share|improve this answer










      answered Nov 16 '18 at 12:44









      todaytoday

      11.6k22239




      11.6k22239













      • perfect, works like a charm

        – Most Wanted
        Nov 16 '18 at 15:03



















      • perfect, works like a charm

        – Most Wanted
        Nov 16 '18 at 15:03

















      perfect, works like a charm

      – Most Wanted
      Nov 16 '18 at 15:03





      perfect, works like a charm

      – Most Wanted
      Nov 16 '18 at 15:03













      0














      The problem is that it uses Theano as a backend and probably you are using tensorflow (you should check your setting once again). You can change it with: 



      import os
      
os.environ['KERAS_BACKEND'] = 'theano'


      This should be done before importing keras






      share|improve this answer




























        0














        The problem is that it uses Theano as a backend and probably you are using tensorflow (you should check your setting once again). You can change it with: 



        import os
        
os.environ['KERAS_BACKEND'] = 'theano'


        This should be done before importing keras






        share|improve this answer


























          0












          0








          0







          The problem is that it uses Theano as a backend and probably you are using tensorflow (you should check your setting once again). You can change it with: 



          import os
          
os.environ['KERAS_BACKEND'] = 'theano'


          This should be done before importing keras






          share|improve this answer













          The problem is that it uses Theano as a backend and probably you are using tensorflow (you should check your setting once again). You can change it with: 



          import os
          
os.environ['KERAS_BACKEND'] = 'theano'


          This should be done before importing keras







          share|improve this answer












          share|improve this answer



          share|improve this answer










          answered Nov 16 '18 at 12:17









          GabeGabe

          322210




          322210























              0














              Well like I wrote in my comment. I got a error with your code. So see that it looks like you have bad shape on input, if you change to input_shape=(28,28,1) then output_shape returns (None, 26, 26, 32)



              I don't know if this is what you are exactly looking for.






              share|improve this answer




























                0














                Well like I wrote in my comment. I got a error with your code. So see that it looks like you have bad shape on input, if you change to input_shape=(28,28,1) then output_shape returns (None, 26, 26, 32)



                I don't know if this is what you are exactly looking for.






                share|improve this answer


























                  0












                  0








                  0







                  Well like I wrote in my comment. I got a error with your code. So see that it looks like you have bad shape on input, if you change to input_shape=(28,28,1) then output_shape returns (None, 26, 26, 32)



                  I don't know if this is what you are exactly looking for.






                  share|improve this answer













                  Well like I wrote in my comment. I got a error with your code. So see that it looks like you have bad shape on input, if you change to input_shape=(28,28,1) then output_shape returns (None, 26, 26, 32)



                  I don't know if this is what you are exactly looking for.







                  share|improve this answer












                  share|improve this answer



                  share|improve this answer










                  answered Nov 16 '18 at 12:22









                  TzomasTzomas

                  517314




                  517314






























                      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














                      StackExchange.ready(
                      function () {
                      StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53337586%2fconvolution2d-gives-wrong-output-shape-in-keras%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

                      Florida Star v. B. J. F.

                      Image
                      Florida Star v. B. J. F. From Wikipedia, the free encyclopedia Jump to navigation Jump to search United States Supreme Court case Florida Star v. B. J. F. Supreme Court of the United States Argued March 21, 1989 Decided June 21, 1989 Full case name The Florida Star v. B. J. F. Citations 491 U.S. 524 ( more ) 109 S. Ct. 2603; 105 L. Ed. 2d 443; 1989 U.S. LEXIS 3120; 57 U.S.L.W. 4816; 16 Media L. Rep. 1801 Prior history The Florida Star v. B.J.F., 530 So.2d 286 (1988) Supreme Court of Florida; Florida Star v. B.J.F., 499 So.2d 883 (1986) Fla. Dist. Court of Appeals Holding Florida Stat. § 794.03 is unconstitutional to the extent it makes the truthful reporting of information that was a matter of public record unlawful, as it violates the First Amendment. Court membership Chief Justice William Rehnquist Associate Justices William J. Brennan Jr.  · Byron White Thurgood Marshall  · Harry Blac...
                      Read more

                      Danny Elfman

                      Image
                      Danny Elfman From Wikipedia, the free encyclopedia Jump to navigation Jump to search Danny Elfman Elfman at the 2010 San Diego Comic-Con Born Daniel Robert Elfman ( 1953-05-29 ) May 29, 1953 (age 65) Los Angeles, California, U.S. Spouse(s) Bridget Fonda ( m.  2003) Children 1 Musical career Genres Rock [1] ska [2] new wave film music video game music Occupation(s) Composer, singer, songwriter, record producer Instruments Trombone guitar percussion vocals keyboards [3] Years active 1972–present Associated acts Oingo Boingo James Newton Howard Daniel Robert Elfman (born May 29, 1953) is an American composer, singer, songwriter, and record producer. Elfman first became known for being the lead singer and songwriter for the band Oingo Boingo from 1974 to 1995. He is well known for scoring films and television shows, particularly his frequent collabora...
                      Read more

                      Lugert, Oklahoma

                      Image
                      Unincorporated community in Oklahoma, United States Lugert, Oklahoma Unincorporated community Foundations from the town of Lugert at the bottom of Lake Altus-Lugert Lugert, Oklahoma Location within the state of Oklahoma Coordinates: 34°53′45″N 99°16′31″W  /  34.89583°N 99.27528°W  / 34.89583; -99.27528 Coordinates: 34°53′45″N 99°16′31″W  /  34.89583°N 99.27528°W  / 34.89583; -99.27528 Country United States State Oklahoma County Kiowa Time zone UTC-6 (Central (CST))  • Summer (DST) UTC-5 (CDT) GNIS feature ID 1100597 Lugert is an unincorporated community in Kiowa County, Oklahoma. [1] The town of Lugert was founded in 1901 on 80 acres (320,000 m 2 ). In the town, there was a general store that housed the Post office and sold dry goods, school supplies, groceries, harnesses, axes and much more. It was named for Frank Lugert, who had moved to the area in 1898. Lugert owned land where the town was sited and also owned the general st...
                      Read more