Styjun

Unexpected route on a flight from USA to Europe

Why can I log in to my Facebook account with a misspelled email/password?

Why does the ultra long-end of a yield curve invert?

Is it double speak?

How to explain to a team that the project they will work for 6 months will 100% fail?

Can an actual attack instead of a feint be used as the distraction for a help action?

Infeasibility in mathematical optimization models

How to realistically deal with a shield user?

Does the Voyager team use a wrapper (Fortran(77?) to Python) to transmit current commands?

What is to be understood by the assertion 'Israels right to exist'?

Does this smartphone photo show Mars just below the Sun?

French equivalent of "Make leaps and bounds"

Is the beaming of this score following a vocal practice or it is just outdated and obscuring the beat?

Look mom! I made my own (Base 10) numeral system!

Our group keeps dying during the Lost Mine of Phandelver campaign. What are we doing wrong?

Does the United States guarantee any unique freedoms?

Does bottle color affect mold growth?

How can glass marbles naturally occur in a desert?

Will a paper be retracted if a flaw in released software code invalidates its central idea?

How to draw a flow chart?

Should I take out a personal loan to pay off credit card debt?

How is the return type of a ternary operator determined?

What word can be used to describe a bug in a movie?

Is it allowed and safe to carry a passenger / non-pilot in the front seat of a small general aviation airplane?

Find parameters of Tensorflow graph

Tensorflow: how to save/restore a model?Display image of graph in TensorFlow?Tensorflow: restoring a graph and model then running evaluation on a single imageHow to get current available GPUs in tensorflow?Session graph is emptyImport a simple Tensorflow frozen_model.pb file and make prediction in C++Extract the weights from a TensorFlow graph to use them in KerasHow to convert a HED model to Tensorflow Lite modelUnable to convert custom trained frozen model into tflite format

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

0

1

I have this TensorFlow graph. I successfully obtained input_arrays and output_arrays of this graph using this script:

import tensorflow as tf
gf = tf.GraphDef() 
m_file = open('deeplabv3_mnv2_pascal_tain.pb','rb')
gf.ParseFromString(m_file.read())

for n in gf.node:
 print( n.name )

I am stuck at a point where I cannot obtain:

input_shapes

from the same graph. How do I get this information provided I only have this graph.

python-3.x tensorflow machine-learning computer-vision

share|improve this question

edited Mar 27 at 6:31

Ajinkya

asked Mar 27 at 6:18

AjinkyaAjinkya

58233 silver badges1818 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  If you are down voting please let me know the reason. I can change my question accordingly. If I still didn't change the question after giving reason then feel free to down vote.
  
  – Ajinkya
  Mar 27 at 6:24
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  
  Your Google drive needs permission. Please try to include that information here if possible. I didn't downvote.
  
  – Mohan Radhakrishnan
  Mar 27 at 7:36
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Ive updated the permissions please try now
  
  – Ajinkya
  Mar 27 at 7:57
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  By input_shapes do you mean the shape of the input (which you already get the name) ?
  
  – Dere_negn
  Mar 27 at 14:35
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  --input_shapes=1,1568,1176,3, means the dimensions of training set. Ive changed them according to my training set
  
  – Ajinkya
  Mar 28 at 12:07
  

  
  
  
  

add a comment | 

0

1

I have this TensorFlow graph. I successfully obtained input_arrays and output_arrays of this graph using this script:

import tensorflow as tf
gf = tf.GraphDef() 
m_file = open('deeplabv3_mnv2_pascal_tain.pb','rb')
gf.ParseFromString(m_file.read())

for n in gf.node:
 print( n.name )

I am stuck at a point where I cannot obtain:

input_shapes

from the same graph. How do I get this information provided I only have this graph.

python-3.x tensorflow machine-learning computer-vision

share|improve this question

edited Mar 27 at 6:31

Ajinkya

asked Mar 27 at 6:18

AjinkyaAjinkya

58233 silver badges1818 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  If you are down voting please let me know the reason. I can change my question accordingly. If I still didn't change the question after giving reason then feel free to down vote.
  
  – Ajinkya
  Mar 27 at 6:24
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  
  Your Google drive needs permission. Please try to include that information here if possible. I didn't downvote.
  
  – Mohan Radhakrishnan
  Mar 27 at 7:36
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Ive updated the permissions please try now
  
  – Ajinkya
  Mar 27 at 7:57
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  By input_shapes do you mean the shape of the input (which you already get the name) ?
  
  – Dere_negn
  Mar 27 at 14:35
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  --input_shapes=1,1568,1176,3, means the dimensions of training set. Ive changed them according to my training set
  
  – Ajinkya
  Mar 28 at 12:07
  

  
  
  
  

add a comment | 

I have this TensorFlow graph. I successfully obtained input_arrays and output_arrays of this graph using this script:

import tensorflow as tf
gf = tf.GraphDef() 
m_file = open('deeplabv3_mnv2_pascal_tain.pb','rb')
gf.ParseFromString(m_file.read())

for n in gf.node:
 print( n.name )

I am stuck at a point where I cannot obtain:

input_shapes

from the same graph. How do I get this information provided I only have this graph.

python-3.x tensorflow machine-learning computer-vision

share|improve this question

edited Mar 27 at 6:31

Ajinkya

asked Mar 27 at 6:18

AjinkyaAjinkya

58233 silver badges1818 bronze badges

import tensorflow as tf
gf = tf.GraphDef() 
m_file = open('deeplabv3_mnv2_pascal_tain.pb','rb')
gf.ParseFromString(m_file.read())

for n in gf.node:
 print( n.name )

input_shapes

share|improve this question

edited Mar 27 at 6:31

Ajinkya

asked Mar 27 at 6:18

AjinkyaAjinkya

58233 silver badges1818 bronze badges

share|improve this question

edited Mar 27 at 6:31

Ajinkya

asked Mar 27 at 6:18

AjinkyaAjinkya

58233 silver badges1818 bronze badges

asked Mar 27 at 6:18

AjinkyaAjinkya

58233 silver badges1818 bronze badges

asked Mar 27 at 6:18

AjinkyaAjinkya

58233 silver badges1818 bronze badges