How to use a TF metric with a model? The Next CEO of Stack Overflow2019 Community Moderator ElectionHow to use lists in Tensorflow?Is it possible to use grayscale images to existing model?How to speed-up trained Tensorflow model with FC layers for productionHow to Save TensorFlow model using estimator.export_savemodel()Custom conditional Keras metricCan I create pretrain model with tensorflow?Why is my Keras model not learning image segmentation?Tensorflow tf.divide how to useHow to run a saved TensorFlow Model? (Video Prediction Model)How to develop custom metric with one class priority Keras

What is the purpose of the Evocation wizard's Potent Cantrip feature?

A "random" question: usage of "random" as adjective in Spanish

Only print output after finding pattern

Rotate a column

Is there a difference between "Fahrstuhl" and "Aufzug"

Return the Closest Prime Number

How to Reset Passwords on Multiple Websites Easily?

If/When UK leaves the EU, can a future goverment do a referendum to join EU

Why do remote companies require working in the US?

Would a galaxy be visible from outside, but nearby?

Extending anchors in TikZ

Example of a Mathematician/Physicist whose Other Publications during their PhD eclipsed their PhD Thesis

Does it take more energy to get to Venus or to Mars?

How do I construct this japanese bowl?

Was a professor correct to chastise me for writing "Prof. X" rather than "Professor X"?

Robert Sheckley short story about vacation spots being overwhelmed

How did people program for Consoles with multiple CPUs?

How long to clear the 'suck zone' of a turbofan after start is initiated?

What does this shorthand mean?

Why did we only see the N-1 starfighters in one film?

Why is the US ranked as #45 in Press Freedom ratings, despite its extremely permissive free speech laws?

Complex fractions

How to get regions to plot as graphics

Monthly twice production release for my software project



How to use a TF metric with a model?



The Next CEO of Stack Overflow
2019 Community Moderator ElectionHow to use lists in Tensorflow?Is it possible to use grayscale images to existing model?How to speed-up trained Tensorflow model with FC layers for productionHow to Save TensorFlow model using estimator.export_savemodel()Custom conditional Keras metricCan I create pretrain model with tensorflow?Why is my Keras model not learning image segmentation?Tensorflow tf.divide how to useHow to run a saved TensorFlow Model? (Video Prediction Model)How to develop custom metric with one class priority Keras










1












$begingroup$


I am trying to compile a simple model and the following works just fine:



model.compile(optimizer=tf.train.AdamOptimizer(0.001),
loss='categorical_crossentropy',
metrics=['accuracy'])


However, I would like to use this metric: tf.metrics.precision_at_k and I am not sure how I can get it to work. It requires two arguments and that is causing an issue as I don't know how to pass predictions as an argument. I tried a



model.compile(optimizer=tf.train.AdamOptimizer(0.001),
loss='categorical_crossentropy',
metrics=[tf.metrics.precision_at_k])


And certain variations but did not help.



Minimal working code:



import tensorflow as tf
from tensorflow.keras import layers
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu, input_shape=(5, 5, 1)),
tf.keras.layers.MaxPooling2D((2, 2), strides=2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation=tf.nn.relu),
tf.keras.layers.Dense(2, activation=tf.nn.softmax)
])









share|improve this question









New contributor




ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$
















    1












    $begingroup$


    I am trying to compile a simple model and the following works just fine:



    model.compile(optimizer=tf.train.AdamOptimizer(0.001),
    loss='categorical_crossentropy',
    metrics=['accuracy'])


    However, I would like to use this metric: tf.metrics.precision_at_k and I am not sure how I can get it to work. It requires two arguments and that is causing an issue as I don't know how to pass predictions as an argument. I tried a



    model.compile(optimizer=tf.train.AdamOptimizer(0.001),
    loss='categorical_crossentropy',
    metrics=[tf.metrics.precision_at_k])


    And certain variations but did not help.



    Minimal working code:



    import tensorflow as tf
    from tensorflow.keras import layers
    model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu, input_shape=(5, 5, 1)),
    tf.keras.layers.MaxPooling2D((2, 2), strides=2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation=tf.nn.relu),
    tf.keras.layers.Dense(2, activation=tf.nn.softmax)
    ])









    share|improve this question









    New contributor




    ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$














      1












      1








      1





      $begingroup$


      I am trying to compile a simple model and the following works just fine:



      model.compile(optimizer=tf.train.AdamOptimizer(0.001),
      loss='categorical_crossentropy',
      metrics=['accuracy'])


      However, I would like to use this metric: tf.metrics.precision_at_k and I am not sure how I can get it to work. It requires two arguments and that is causing an issue as I don't know how to pass predictions as an argument. I tried a



      model.compile(optimizer=tf.train.AdamOptimizer(0.001),
      loss='categorical_crossentropy',
      metrics=[tf.metrics.precision_at_k])


      And certain variations but did not help.



      Minimal working code:



      import tensorflow as tf
      from tensorflow.keras import layers
      model = tf.keras.Sequential([
      tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu, input_shape=(5, 5, 1)),
      tf.keras.layers.MaxPooling2D((2, 2), strides=2),
      tf.keras.layers.Flatten(),
      tf.keras.layers.Dense(128, activation=tf.nn.relu),
      tf.keras.layers.Dense(2, activation=tf.nn.softmax)
      ])









      share|improve this question









      New contributor




      ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      I am trying to compile a simple model and the following works just fine:



      model.compile(optimizer=tf.train.AdamOptimizer(0.001),
      loss='categorical_crossentropy',
      metrics=['accuracy'])


      However, I would like to use this metric: tf.metrics.precision_at_k and I am not sure how I can get it to work. It requires two arguments and that is causing an issue as I don't know how to pass predictions as an argument. I tried a



      model.compile(optimizer=tf.train.AdamOptimizer(0.001),
      loss='categorical_crossentropy',
      metrics=[tf.metrics.precision_at_k])


      And certain variations but did not help.



      Minimal working code:



      import tensorflow as tf
      from tensorflow.keras import layers
      model = tf.keras.Sequential([
      tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu, input_shape=(5, 5, 1)),
      tf.keras.layers.MaxPooling2D((2, 2), strides=2),
      tf.keras.layers.Flatten(),
      tf.keras.layers.Dense(128, activation=tf.nn.relu),
      tf.keras.layers.Dense(2, activation=tf.nn.softmax)
      ])






      deep-learning tensorflow






      share|improve this question









      New contributor




      ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question









      New contributor




      ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question








      edited Mar 22 at 19:39







      ste_kwr













      New contributor




      ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked Mar 22 at 17:12









      ste_kwrste_kwr

      1063




      1063




      New contributor




      ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      ste_kwr is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.




















          0






          active

          oldest

          votes












          Your Answer





          StackExchange.ifUsing("editor", function ()
          return StackExchange.using("mathjaxEditing", function ()
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          );
          );
          , "mathjax-editing");

          StackExchange.ready(function()
          var channelOptions =
          tags: "".split(" "),
          id: "557"
          ;
          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: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          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
          );



          );






          ste_kwr is a new contributor. Be nice, and check out our Code of Conduct.









          draft saved

          draft discarded


















          StackExchange.ready(
          function ()
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47805%2fhow-to-use-a-tf-metric-with-a-model%23new-answer', 'question_page');

          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          ste_kwr is a new contributor. Be nice, and check out our Code of Conduct.









          draft saved

          draft discarded


















          ste_kwr is a new contributor. Be nice, and check out our Code of Conduct.












          ste_kwr is a new contributor. Be nice, and check out our Code of Conduct.











          ste_kwr is a new contributor. Be nice, and check out our Code of Conduct.














          Thanks for contributing an answer to Data Science Stack Exchange!


          • 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.

          Use MathJax to format equations. MathJax reference.


          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%2fdatascience.stackexchange.com%2fquestions%2f47805%2fhow-to-use-a-tf-metric-with-a-model%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

          Rank groups within a grouped sequence of TRUE/FALSE and NAGrouping functions (tapply, by, aggregate) and the *apply familyCharacters counting and subletting specific patternsWhat is the purpose of setting a key in data.table?data.table vs dplyr: can one do something well the other can't or does poorly?how to make a bar plot for a list of dataframes?How to group by unique values in a list in RPandas - Alternative to rank() function that gives unique ordinal ranks for a columnRank within group in for loop in RData transformation: from dyadic to observational data in RGetting map from purrr to work with paste0

          Are all passive ability checks floors for active ability checks?Does passive perception supersede active perception?Which skills can be used passively?Active Opposition with Free-Form Professions in Fate5E Trap/Ambush/Stealth Mechanics VS Passive Perception ConfusionInteraction between perception and stealth in obscured conditionsHow does Keen Sight affect Passive Perception?Are all d20 rolls either attacks, saves or ability checks?Can players declare that they are making a specific ability check?Can I see a Hidden creature that is not obscured at all?Can a Stealth check ever be made passively?Is this alternate version of the Observant feat balanced?What is the minimum amount of skill points per HD?

          Quoting Keynes in a lectureIs differentiated instruction permitted by universities?How to make students learn prerequisitesUnsatisfactory Instructor Evaluations: balancing of expectations of engineering studentsWhat is the difference between a “statistician”, “applied statistician”, and an academic applying advanced stats within their field?Listing in reference section, but not quotingHow to efficiently use time while preparing for a class?Graduate Admissions: Teaching Emphasisstrategies for sharing teaching information with universities I don't personally have contacts withIs there an efficient way to give a large class of students feedback about their assignments?Is it unreasonable to expect students to read the lecture notes before attending the first class?