Styjun

Does Dispel Magic destroy Artificer Turrets?

How likely is fragmentation on a table with 40000 products likely to affect performance

Why did I lose on time with 3 pawns vs Knight. Shouldn't it be a draw?

How can Paypal know my card is being used in another account?

Irreducible factors of primitive permutation group representation

Do the books ever say oliphaunts aren’t elephants?

What did G-d do before Creation?

Why force the nose of 737 Max down in the first place?

Is there a wealth gap in Boston where the median net worth of white households is $247,500 while the median net worth for black families was $8?

Why is の所 used after ドア in this sentence?

What do I do with a party that is much stronger than their level?

Does dual boot harm a laptop battery or reduce its life?

Why did some Apollo missions carry a grenade launcher?

ECDSA: Why is SigningKey shorter than VerifyingKey

2 weeks and a tight budget to prepare for Z-day. How long can I hunker down?

If Trump gets impeached, how long would Pence be president?

To find islands of 1 and 0 in matrix

How do I use JSON.generator to generate an unnamed array?

Must a song using the A minor scale begin or end with an Am chord? If not, how can I tell what the scale is?

8086 stack segment and avoiding overflow in interrupts

Is there a way to know the composition of a Team GO Rocket before going into the fight?

What is more environmentally friendly? An A320 or a car?

Is it error of law to judge on less relevant case law when there is much more relevant one?

Name These Animals

keras.load_model() can't recognize Tensorflow's activation functions

ValueError: Output tensors to a Model must be the output of a TensorFlow Layer with tf.keras Lambda layerCan't import frozen graph after adding layers to Keras modelCan't save custom subclassed modelKeras custom activation function (not training)Error when loading Keras model trained by tensorflowError on trying to extract frozen tensorflow graphCannot Reload saved Keras model using tensorflowWhy tensorflow.contrib.framework.arg_scope not applicable to tf.keras.layers?Can't use tf.keras.optimizer with tf.keras.models.sequentialImport Keras directly or through TensorFlow? Should I uninstall either one?

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;

0

I saved a tf.keras model using tf.keras.save_model functions.
why tf.keras.load_model throws an exception?

code example:

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
 layers.Dense(8, activation=tf.nn.leaky_relu),
 layers.Dense(8, activation=tf.nn.leaky_relu)
])

tf.keras.models.save_model(
 model,
 'model'
)

tf.keras.models.load_model('model')

I expect this code to load the model, but it throws an exception:

ValueError: Unknown activation function:leaky_relu

thanks for your help !

tensorflow keras tf.keras

share|improve this question

asked Mar 26 at 19:31

noam gaashnoam gaash

921111 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  This absolutely should work. Paste full code
  
  – Sharky
  Mar 26 at 19:39
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  @Sharky this is the full code. see colab example: colab.research.google.com/drive/…
  
  – noam gaash
  Mar 26 at 19:41
  
  

  
  
  
  

add a comment | 

0

I saved a tf.keras model using tf.keras.save_model functions.
why tf.keras.load_model throws an exception?

code example:

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
 layers.Dense(8, activation=tf.nn.leaky_relu),
 layers.Dense(8, activation=tf.nn.leaky_relu)
])

tf.keras.models.save_model(
 model,
 'model'
)

tf.keras.models.load_model('model')

I expect this code to load the model, but it throws an exception:

ValueError: Unknown activation function:leaky_relu

thanks for your help !

tensorflow keras tf.keras

share|improve this question

asked Mar 26 at 19:31

noam gaashnoam gaash

921111 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  This absolutely should work. Paste full code
  
  – Sharky
  Mar 26 at 19:39
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  @Sharky this is the full code. see colab example: colab.research.google.com/drive/…
  
  – noam gaash
  Mar 26 at 19:41
  
  

  
  
  
  

add a comment | 

I saved a tf.keras model using tf.keras.save_model functions.
why tf.keras.load_model throws an exception?

code example:

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
 layers.Dense(8, activation=tf.nn.leaky_relu),
 layers.Dense(8, activation=tf.nn.leaky_relu)
])

tf.keras.models.save_model(
 model,
 'model'
)

tf.keras.models.load_model('model')

I expect this code to load the model, but it throws an exception:

ValueError: Unknown activation function:leaky_relu

thanks for your help !

tensorflow keras tf.keras

share|improve this question

asked Mar 26 at 19:31

noam gaashnoam gaash

921111 bronze badges

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
 layers.Dense(8, activation=tf.nn.leaky_relu),
 layers.Dense(8, activation=tf.nn.leaky_relu)
])

tf.keras.models.save_model(
 model,
 'model'
)

tf.keras.models.load_model('model')

share|improve this question

asked Mar 26 at 19:31

noam gaashnoam gaash

921111 bronze badges

share|improve this question

asked Mar 26 at 19:31

noam gaashnoam gaash

921111 bronze badges

asked Mar 26 at 19:31

noam gaashnoam gaash

921111 bronze badges

asked Mar 26 at 19:31

noam gaashnoam gaash

921111 bronze badges

1 Answer
1

active

oldest

votes

2

You need to add custom objects

tf.keras.models.load_model('model', custom_objects='leaky_relu': tf.nn.leaky_relu)

share|improve this answer

answered Mar 26 at 20:00

SharkySharky

2,71422 gold badges99 silver badges1919 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  wow, that's working perfect! thank you !
  
  – noam gaash
  Mar 26 at 20:07
  

  
  
  
  

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

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f55364954%2fkeras-load-model-cant-recognize-tensorflows-activation-functions%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

2

You need to add custom objects

tf.keras.models.load_model('model', custom_objects='leaky_relu': tf.nn.leaky_relu)

share|improve this answer

answered Mar 26 at 20:00

SharkySharky

2,71422 gold badges99 silver badges1919 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  wow, that's working perfect! thank you !
  
  – noam gaash
  Mar 26 at 20:07
  

  
  
  
  

add a comment | 

2

You need to add custom objects

tf.keras.models.load_model('model', custom_objects='leaky_relu': tf.nn.leaky_relu)

share|improve this answer

answered Mar 26 at 20:00

SharkySharky

2,71422 gold badges99 silver badges1919 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  wow, that's working perfect! thank you !
  
  – noam gaash
  Mar 26 at 20:07
  

  
  
  
  

add a comment | 

You need to add custom objects

tf.keras.models.load_model('model', custom_objects='leaky_relu': tf.nn.leaky_relu)

share|improve this answer

answered Mar 26 at 20:00

SharkySharky

2,71422 gold badges99 silver badges1919 bronze badges

tf.keras.models.load_model('model', custom_objects='leaky_relu': tf.nn.leaky_relu)

share|improve this answer

answered Mar 26 at 20:00

SharkySharky

2,71422 gold badges99 silver badges1919 bronze badges

answered Mar 26 at 20:00

SharkySharky

2,71422 gold badges99 silver badges1919 bronze badges

answered Mar 26 at 20:00

SharkySharky

2,71422 gold badges99 silver badges1919 bronze badges