Trjtdtk

Identifying the interval from A♭ to D♯

Can I get a Visa Waiver after spending 6 months in USA with B-2 Visa?

PTIJ: Who should I vote for? (21st Knesset Edition)

Welcoming 2019 Pi day: How to draw the letter π?

Declaring defaulted assignment operator as constexpr: which compiler is right?

How to write cleanly even if my character uses expletive language?

Better performance for geohash aggregation with PostGIS

How do anti-virus programs start at Windows boot?

Employee lack of ownership

Backup with Hanoi Strategy

Create shipment and invoice in mass action

What does it mean to make a bootable LiveUSB?

Software described as 香ばしい

What are substitutions for coconut in curry?

Brexit - No Deal Rejection

Recruiter wants very extensive technical details about all of my previous work

Happy pi day, everyone!

shell script to pass values properties file in java

newcommand: Combine (optional) star and optional parameter

Why do Australian milk farmers need to protest supermarkets' milk price?

How to prevent Firefox and Chrome from opening ports in the firewall?

Should we release the security issues we found in our product as CVE or we can just update those on weekly release notes?

At what level can a dragon innately cast its spells?

How to deal with a cynical class?

Kronecker product using sparse matrices / tensors in tensorflow

Tensorflow neural network TypeError: Fetch argument has invalid typeTesting a tensorflow network: in_top_k() replacement for multilabel classificationPyTorch vs. Tensorflow FoldFine-tuning a model from an existing checkpoint with TensorFlow-SlimMNIST Deep Neural Network using TensorFlowLSTM Implementation using tensorflow (anaconda)Improve test accuracy for TensorFlow CNNHow does one interpret output from hyper-engine while optimizing a single hyperparameter of a neural network?Neural network model for sparse multi-class classifier on TensorflowUsing Keras masking layer with 2D convolutions (Conv2D)

1

$begingroup$

I am currently trying to perform a kronecker product on a pair of sparse tensors in tensorflow. I have found some code on another thread to perform the kronecker product using normal tensors.

def tf_kron(a,b):
 a_shape = [a.shape[0].value,a.shape[1].value]
 b_shape = [b.shape[0].value,b.shape[1].value]
 return tf.reshape(tf.reshape(a,[a_shape[0],1,a_shape[1],1])*tf.reshape(b,[1,b_shape[0],1,b_shape[1]]),[a_shape[0]*b_shape[0],a_shape[1]*b_shape[1]])

However this is not the case with sparse tensors. I'm not fully aware of how to reshape sparse tensors.

python deep-learning tensorflow

share|improve this question

edited yesterday

DeepLearner

asked yesterday

DeepLearnerDeepLearner

405

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  It would be helpful to be a bit more specific about your problem... What have you tried so far - or found elsewhere - that didn't help you?
  $endgroup$
  – n1k31t4
  yesterday
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  This is the code I have used on regular tensors.
  $endgroup$
  – DeepLearner
  yesterday
  

  
  
  
  

add a comment | 

1

$begingroup$

I am currently trying to perform a kronecker product on a pair of sparse tensors in tensorflow. I have found some code on another thread to perform the kronecker product using normal tensors.

def tf_kron(a,b):
 a_shape = [a.shape[0].value,a.shape[1].value]
 b_shape = [b.shape[0].value,b.shape[1].value]
 return tf.reshape(tf.reshape(a,[a_shape[0],1,a_shape[1],1])*tf.reshape(b,[1,b_shape[0],1,b_shape[1]]),[a_shape[0]*b_shape[0],a_shape[1]*b_shape[1]])

However this is not the case with sparse tensors. I'm not fully aware of how to reshape sparse tensors.

python deep-learning tensorflow

share|improve this question

edited yesterday

DeepLearner

asked yesterday

DeepLearnerDeepLearner

405

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  It would be helpful to be a bit more specific about your problem... What have you tried so far - or found elsewhere - that didn't help you?
  $endgroup$
  – n1k31t4
  yesterday
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  This is the code I have used on regular tensors.
  $endgroup$
  – DeepLearner
  yesterday
  

  
  
  
  

add a comment | 

$begingroup$

I am currently trying to perform a kronecker product on a pair of sparse tensors in tensorflow. I have found some code on another thread to perform the kronecker product using normal tensors.

def tf_kron(a,b):
 a_shape = [a.shape[0].value,a.shape[1].value]
 b_shape = [b.shape[0].value,b.shape[1].value]
 return tf.reshape(tf.reshape(a,[a_shape[0],1,a_shape[1],1])*tf.reshape(b,[1,b_shape[0],1,b_shape[1]]),[a_shape[0]*b_shape[0],a_shape[1]*b_shape[1]])

However this is not the case with sparse tensors. I'm not fully aware of how to reshape sparse tensors.

python deep-learning tensorflow

share|improve this question

edited yesterday

DeepLearner

asked yesterday

DeepLearnerDeepLearner

405

$endgroup$

def tf_kron(a,b):
 a_shape = [a.shape[0].value,a.shape[1].value]
 b_shape = [b.shape[0].value,b.shape[1].value]
 return tf.reshape(tf.reshape(a,[a_shape[0],1,a_shape[1],1])*tf.reshape(b,[1,b_shape[0],1,b_shape[1]]),[a_shape[0]*b_shape[0],a_shape[1]*b_shape[1]])

share|improve this question

edited yesterday

DeepLearner

asked yesterday

DeepLearnerDeepLearner

405

share|improve this question

edited yesterday

DeepLearner

asked yesterday

DeepLearnerDeepLearner

405

asked yesterday

DeepLearnerDeepLearner

405

asked yesterday

DeepLearnerDeepLearner

405