Styjun

Are PMR446 walkie-talkies legal in Switzerland?

Why does Bran want to find Drogon?

Why was this character made Grand Maester?

How to remove new line added by readarray when using a delimiter?

Ribbon Cable Cross Talk - Is there a fix after the fact?

Is it normal to "extract a paper" from a master thesis?

Visual Block Mode edit with sequential number

Why do the i8080 I/O instructions take a byte-sized operand to determine the port?

How to find sum of maximum K elements in range in array

Are runways booked by airlines to land their planes?

ifconfig shows UP while ip link shows DOWN

Why'd a rational buyer offer to buy with no conditions precedent?

Why is std::ssize() introduced in C++20

resolution bandwidth

Testing using real data of the customer

How to escape dependency hell?

The disk image is 497GB smaller than the target device

Paired t-test means that the variances of the 2 samples are the same?

Writing "hahaha" versus describing the laugh

Set outline first and fill colors later

Using too much dialogue?

Did Game of Thrones end the way that George RR Martin intended?

Is "vegetable base" a common term in English?

What is the limit to a Glyph of Warding's trigger?

What are the parameters input_arrays and output_arrays that are needed to convert a frozen model '.pb' file to a '.tflite' file?

Tensorflow: How to get a tensor by name?Given a tensor flow model graph, how to find the input node and output node namesDefine input and output tensors for tf.lite.TocoConverterTensorflow Convert pb file to TFLITE using pythonTensorFlow saved model export conversion to tfliteHow can I view weights in a .tflite file?How can you identify Input and Output name in tensorboard graph like this one in the pictures attached to this post?How to convert .pb to TFLite format?How to convert a HED model to Tensorflow Lite modelissue with converting keras h5 model file to tflite - Type Error('keyword argument not understood: ', 'interpolation')Convert Keras MobileNet model to TFLite with 8-bit quantizationHow to convert Dlib weights into tflite format?How to read parameters of layers of .tflite model in python

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

1

I need to convert my .pb tensorflow model together with my .cpkt file to a tflite model to make it work in Mobile Devices. Is there any straight-forward way to find out how can I find what are the parameters I should use for input_arrays and output_arrays?

import tensorflow as tf

graph_def_file = "/path/to/Downloads/mobilenet_v1_1.0_224/frozen_graph.pb"
input_arrays = ["input"]
output_arrays = ["MobilenetV1/Predictions/Softmax"]

converter = tf.lite.TFLiteConverter.from_frozen_graph(
 graph_def_file, input_arrays, output_arrays)
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

tensorflow keras tensorflow-lite yolo

share|improve this question

edited Mar 24 at 7:30

gameon67

1,345926

asked Mar 23 at 21:12

DaniDani

103

add a comment | 

1

I need to convert my .pb tensorflow model together with my .cpkt file to a tflite model to make it work in Mobile Devices. Is there any straight-forward way to find out how can I find what are the parameters I should use for input_arrays and output_arrays?

import tensorflow as tf

graph_def_file = "/path/to/Downloads/mobilenet_v1_1.0_224/frozen_graph.pb"
input_arrays = ["input"]
output_arrays = ["MobilenetV1/Predictions/Softmax"]

converter = tf.lite.TFLiteConverter.from_frozen_graph(
 graph_def_file, input_arrays, output_arrays)
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

tensorflow keras tensorflow-lite yolo

share|improve this question

edited Mar 24 at 7:30

gameon67

1,345926

asked Mar 23 at 21:12

DaniDani

103

add a comment | 

I need to convert my .pb tensorflow model together with my .cpkt file to a tflite model to make it work in Mobile Devices. Is there any straight-forward way to find out how can I find what are the parameters I should use for input_arrays and output_arrays?

import tensorflow as tf

graph_def_file = "/path/to/Downloads/mobilenet_v1_1.0_224/frozen_graph.pb"
input_arrays = ["input"]
output_arrays = ["MobilenetV1/Predictions/Softmax"]

converter = tf.lite.TFLiteConverter.from_frozen_graph(
 graph_def_file, input_arrays, output_arrays)
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

tensorflow keras tensorflow-lite yolo

share|improve this question

edited Mar 24 at 7:30

gameon67

1,345926

asked Mar 23 at 21:12

DaniDani

103

import tensorflow as tf

graph_def_file = "/path/to/Downloads/mobilenet_v1_1.0_224/frozen_graph.pb"
input_arrays = ["input"]
output_arrays = ["MobilenetV1/Predictions/Softmax"]

converter = tf.lite.TFLiteConverter.from_frozen_graph(
 graph_def_file, input_arrays, output_arrays)
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

share|improve this question

edited Mar 24 at 7:30

gameon67

1,345926

asked Mar 23 at 21:12

DaniDani

103

share|improve this question

edited Mar 24 at 7:30

gameon67

1,345926

asked Mar 23 at 21:12

DaniDani

103

edited Mar 24 at 7:30

gameon67

1,345926

edited Mar 24 at 7:30

gameon67

1,345926

asked Mar 23 at 21:12

DaniDani

103

asked Mar 23 at 21:12

DaniDani

103

1 Answer
1

active

oldest

votes

0

According to the official docs here :

input_arrays: List of input tensors to freeze graph with.

output_arrays: List of output tensors to freeze graph with.

Meaning, input_arrays is the list of input tensors ( which are mostly placeholder tensors ). output_arrays is the list of Tensor objects which will act as outputs.

In your case, you are providing the name of the Tensor object. An actual Tensor object is required.

You can understand it with this example:

x1 = tf.placeholder( dtype=tf.float32 )
x2 = tf.placeholder( dtype=tf.float32 )
y = x1 + x2

input_arrays = [ x1 , x2 ]
output_arrays = [ y ]

You can learn to find the input and output tensors from here .
Seeing your code, it seems that you know the tensor names, so you can refer this answer.

share|improve this answer

answered Mar 24 at 2:32

Shubham PanchalShubham Panchal

9051212

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  So, you mean I must provide the tensors itself instead if the names? Thanks very much
  
  – Dani
  Mar 24 at 9:57
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Yes. Provide the tensors and not their names. Also, accept the answer if it feels helpful.
  
  – Shubham Panchal
  Mar 24 at 10:38
  

  
  
  
  

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%2f55318440%2fwhat-are-the-parameters-input-arrays-and-output-arrays-that-are-needed-to-conver%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

According to the official docs here :

input_arrays: List of input tensors to freeze graph with.

output_arrays: List of output tensors to freeze graph with.

Meaning, input_arrays is the list of input tensors ( which are mostly placeholder tensors ). output_arrays is the list of Tensor objects which will act as outputs.

In your case, you are providing the name of the Tensor object. An actual Tensor object is required.

You can understand it with this example:

x1 = tf.placeholder( dtype=tf.float32 )
x2 = tf.placeholder( dtype=tf.float32 )
y = x1 + x2

input_arrays = [ x1 , x2 ]
output_arrays = [ y ]

You can learn to find the input and output tensors from here .
Seeing your code, it seems that you know the tensor names, so you can refer this answer.

share|improve this answer

answered Mar 24 at 2:32

Shubham PanchalShubham Panchal

9051212

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  So, you mean I must provide the tensors itself instead if the names? Thanks very much
  
  – Dani
  Mar 24 at 9:57
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Yes. Provide the tensors and not their names. Also, accept the answer if it feels helpful.
  
  – Shubham Panchal
  Mar 24 at 10:38
  

  
  
  
  

add a comment | 

0

According to the official docs here :

input_arrays: List of input tensors to freeze graph with.

output_arrays: List of output tensors to freeze graph with.

Meaning, input_arrays is the list of input tensors ( which are mostly placeholder tensors ). output_arrays is the list of Tensor objects which will act as outputs.

In your case, you are providing the name of the Tensor object. An actual Tensor object is required.

You can understand it with this example:

x1 = tf.placeholder( dtype=tf.float32 )
x2 = tf.placeholder( dtype=tf.float32 )
y = x1 + x2

input_arrays = [ x1 , x2 ]
output_arrays = [ y ]

You can learn to find the input and output tensors from here .
Seeing your code, it seems that you know the tensor names, so you can refer this answer.

share|improve this answer

answered Mar 24 at 2:32

Shubham PanchalShubham Panchal

9051212

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  So, you mean I must provide the tensors itself instead if the names? Thanks very much
  
  – Dani
  Mar 24 at 9:57
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Yes. Provide the tensors and not their names. Also, accept the answer if it feels helpful.
  
  – Shubham Panchal
  Mar 24 at 10:38
  

  
  
  
  

add a comment | 

According to the official docs here :

input_arrays: List of input tensors to freeze graph with.

output_arrays: List of output tensors to freeze graph with.

Meaning, input_arrays is the list of input tensors ( which are mostly placeholder tensors ). output_arrays is the list of Tensor objects which will act as outputs.

In your case, you are providing the name of the Tensor object. An actual Tensor object is required.

You can understand it with this example:

x1 = tf.placeholder( dtype=tf.float32 )
x2 = tf.placeholder( dtype=tf.float32 )
y = x1 + x2

input_arrays = [ x1 , x2 ]
output_arrays = [ y ]

You can learn to find the input and output tensors from here .
Seeing your code, it seems that you know the tensor names, so you can refer this answer.

share|improve this answer

answered Mar 24 at 2:32

Shubham PanchalShubham Panchal

9051212

x1 = tf.placeholder( dtype=tf.float32 )
x2 = tf.placeholder( dtype=tf.float32 )
y = x1 + x2

input_arrays = [ x1 , x2 ]
output_arrays = [ y ]

share|improve this answer

answered Mar 24 at 2:32

Shubham PanchalShubham Panchal

9051212

answered Mar 24 at 2:32

Shubham PanchalShubham Panchal

9051212

answered Mar 24 at 2:32

Shubham PanchalShubham Panchal

9051212