Styjun

How to re-create Edward Weson's Pepper No. 30?

Why is the design of haulage companies so “special”?

Representing power series as a function - what to do with the constant after integration?

Theorems that impeded progress

Why doesn't Newton's third law mean a person bounces back to where they started when they hit the ground?

I’m planning on buying a laser printer but concerned about the life cycle of toner in the machine

Today is the Center

Is it tax fraud for an individual to declare non-taxable revenue as taxable income? (US tax laws)

Why Is Death Allowed In the Matrix?

What is the offset in a seaplane's hull?

XeLaTeX and pdfLaTeX ignore hyphenation

"You are your self first supporter", a more proper way to say it

A function which translates a sentence to title-case

Accidentally leaked the solution to an assignment, what to do now? (I'm the prof)

When blogging recipes, how can I support both readers who want the narrative/journey and ones who want the printer-friendly recipe?

Motorized valve interfering with button?

Python: Add Submenu

What do you call something that goes against the spirit of the law, but is legal when interpreting the law to the letter?

"which" command doesn't work / path of Safari?

Download, install and reboot computer at night if needed

How to add power-LED to my small amplifier?

How to report a triplet of septets in NMR tabulation?

Copenhagen passport control - US citizen

Why don't electron-positron collisions release infinite energy?

How to expand dims of my Keras layer and avoid using Lambda layer

Keras: Use the same layer in different models (share weights)Unable to understand how lambda layer work in keras?Keras Lambda Layer giving ValueError: None values not supported when trying to fit modelWrap tensorflow function in keras layerHow to load MobileNet weights with an input tensor in KerasHow to Build a 2D Weights Matrix in Keras?Multiple Embedding layers for Keras Sequential modelValueError: Output tensors to a Model must be the output of a TensorFlow Layer with tf.keras Lambda layerThe initial state or constants of an RNN layer cannot be specified with a mix of Keras tensors and non-Keras tensors3 dimensional array as input with Embedding Layer and LSTM in Keras

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

0

1

I' m using tensorflow.js and try to convert my keras model to tf.js model. However, it doesn't support Lambda layer which I try to use to convert tensorto layer(I use expand_dims) in my model(If not use it, model won't be created correctly, you know the reason). So I wonder if there is any way that I can avoid using Lambda layer and expand the dim of my embedding_layer.

# input layer
input_x = Input(shape=(sequence_length, ), dtype='int32')

# embedding layer
embedding_layer = Embedding(vocab_size,
 embedding_size,
 embeddings_initializer=random_uniform(minval=-1.0, maxval=1.0))(input_x)
embedded_sequences = Lambda(lambda x: expand_dims(x, -1))(embedding_layer)

I'll appreciate it if you could give me some help, thanks!

tensorflow keras

share|improve this question

asked Mar 22 at 0:43

Jackie SwockyJackie Swocky

133

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  js.tensorflow.org/api/0.15.3/#expandDims
  
  – Manoj Mohan
  Mar 22 at 1:24
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  But my model is converted from Keras, so I can't expand dim of the model in js, it's fixed in "model.json".
  
  – Jackie Swocky
  Mar 22 at 2:28
  

  
  
  
  

add a comment | 

0

1

I' m using tensorflow.js and try to convert my keras model to tf.js model. However, it doesn't support Lambda layer which I try to use to convert tensorto layer(I use expand_dims) in my model(If not use it, model won't be created correctly, you know the reason). So I wonder if there is any way that I can avoid using Lambda layer and expand the dim of my embedding_layer.

# input layer
input_x = Input(shape=(sequence_length, ), dtype='int32')

# embedding layer
embedding_layer = Embedding(vocab_size,
 embedding_size,
 embeddings_initializer=random_uniform(minval=-1.0, maxval=1.0))(input_x)
embedded_sequences = Lambda(lambda x: expand_dims(x, -1))(embedding_layer)

I'll appreciate it if you could give me some help, thanks!

tensorflow keras

share|improve this question

asked Mar 22 at 0:43

Jackie SwockyJackie Swocky

133

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  js.tensorflow.org/api/0.15.3/#expandDims
  
  – Manoj Mohan
  Mar 22 at 1:24
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  But my model is converted from Keras, so I can't expand dim of the model in js, it's fixed in "model.json".
  
  – Jackie Swocky
  Mar 22 at 2:28
  

  
  
  
  

add a comment | 

I' m using tensorflow.js and try to convert my keras model to tf.js model. However, it doesn't support Lambda layer which I try to use to convert tensorto layer(I use expand_dims) in my model(If not use it, model won't be created correctly, you know the reason). So I wonder if there is any way that I can avoid using Lambda layer and expand the dim of my embedding_layer.

# input layer
input_x = Input(shape=(sequence_length, ), dtype='int32')

# embedding layer
embedding_layer = Embedding(vocab_size,
 embedding_size,
 embeddings_initializer=random_uniform(minval=-1.0, maxval=1.0))(input_x)
embedded_sequences = Lambda(lambda x: expand_dims(x, -1))(embedding_layer)

I'll appreciate it if you could give me some help, thanks!

tensorflow keras

share|improve this question

asked Mar 22 at 0:43

Jackie SwockyJackie Swocky

133

# input layer
input_x = Input(shape=(sequence_length, ), dtype='int32')

# embedding layer
embedding_layer = Embedding(vocab_size,
 embedding_size,
 embeddings_initializer=random_uniform(minval=-1.0, maxval=1.0))(input_x)
embedded_sequences = Lambda(lambda x: expand_dims(x, -1))(embedding_layer)

share|improve this question

asked Mar 22 at 0:43

Jackie SwockyJackie Swocky

133

share|improve this question

asked Mar 22 at 0:43

Jackie SwockyJackie Swocky

133

asked Mar 22 at 0:43

Jackie SwockyJackie Swocky

133

asked Mar 22 at 0:43

Jackie SwockyJackie Swocky

133

1 Answer
1

active

oldest

votes

0

I solved it by myself.
Just use reshape.

from keras.backend import int_shape
 ......
 embedded_sequences = Reshape((int_shape(embedding_layer)[1], int_shape(embedding_layer)[2], 1))(embedding_layer)
 ......

You could expand dim without using expand_dims and Lambda layer.

share|improve this answer

answered Mar 22 at 4:06

Jackie SwockyJackie Swocky

133

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%2f55291277%2fhow-to-expand-dims-of-my-keras-layer-and-avoid-using-lambda-layer%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

I solved it by myself.
Just use reshape.

from keras.backend import int_shape
 ......
 embedded_sequences = Reshape((int_shape(embedding_layer)[1], int_shape(embedding_layer)[2], 1))(embedding_layer)
 ......

You could expand dim without using expand_dims and Lambda layer.

share|improve this answer

answered Mar 22 at 4:06

Jackie SwockyJackie Swocky

133

add a comment | 

0

I solved it by myself.
Just use reshape.

from keras.backend import int_shape
 ......
 embedded_sequences = Reshape((int_shape(embedding_layer)[1], int_shape(embedding_layer)[2], 1))(embedding_layer)
 ......

You could expand dim without using expand_dims and Lambda layer.

share|improve this answer

answered Mar 22 at 4:06

Jackie SwockyJackie Swocky

133

add a comment | 

I solved it by myself.
Just use reshape.

from keras.backend import int_shape
 ......
 embedded_sequences = Reshape((int_shape(embedding_layer)[1], int_shape(embedding_layer)[2], 1))(embedding_layer)
 ......

You could expand dim without using expand_dims and Lambda layer.

share|improve this answer

answered Mar 22 at 4:06

Jackie SwockyJackie Swocky

133

from keras.backend import int_shape
 ......
 embedded_sequences = Reshape((int_shape(embedding_layer)[1], int_shape(embedding_layer)[2], 1))(embedding_layer)
 ......

share|improve this answer

answered Mar 22 at 4:06

Jackie SwockyJackie Swocky

133

answered Mar 22 at 4:06

Jackie SwockyJackie Swocky

133

answered Mar 22 at 4:06

Jackie SwockyJackie Swocky

133