Trjtdtk

How is the Swiss post e-voting system supposed to work, and how was it wrong?

Have researchers managed to "reverse time"? If so, what does that mean for physics?

How could a female member of a species produce eggs unto death?

Why did it take so long to abandon sail after steamships were demonstrated?

When do we add an hyphen (-) to a complex adjective word?

Instead of Universal Basic Income, why not Universal Basic NEEDS?

How to explain that I do not want to visit a country due to personal safety concern?

Problems with making formula look great

Russian cases: A few examples, I'm really confused

How to deal with taxi scam when on vacation?

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

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

Min function accepting varying number of arguments in C++17

How do I hide Chekhov's Gun?

I need to drive a 7/16" nut but am unsure how to use the socket I bought for my screwdriver

Did Ender ever learn that he killed Stilson and/or Bonzo?

Can anyone tell me why this program fails?

Be in awe of my brilliance!

How do anti-virus programs start at Windows boot?

Is it possible that AIC = BIC?

Would it take an action or something similar to activate the blindsight property of a Dragon Mask?

How to make healing in an exploration game interesting

Software described as 香ばしい

What is IP squat space

Keras regularizers (kernel, bias and activity) vs tf.contrib.layers.apply_regularization

Tensorflow RNN: Batching data of different lengthRecurrent neural network multiple types of input Kerasshape of theano tensor variable out of keras Conv2DRNN for classification giving vastly different results (Keras)How to Create Shared Weights Layer in KerasMulti-label classifciation: keras custom metricsCan I make some nodes in keras immune to regularization?Subsequent convolution layersHow to optimally train deep learning model using output as new inputProduction: TensorFlow and Keras

1

$begingroup$

I have a DCGAN set up in tensorflow that is working well on the faces in the wild dataset. As an experiment, I tried using the same architecture in keras to better understand the difference in implementation. Performance so far is much worse in keras, but there are a few things I'm uncertain about how they translate, esp regularizer.

In tf, I apply the regularizer with

tf.contrib.layers.apply_regularization

Which is just applied to the whole network it seems. However in keras this must be specified in each layer, and there are three different kinds, kernel, bias and activity regularizer.

I'm trying to udnerstand how they differ, if tf regularizer applies one of the 3 keras types, and how to implement it the same way - do I call it in each convolutional layer including the final output layer? which of the 3 is equivalent of the default regularizer in tf?

Thanks

keras tensorflow convolution gan regularization

share|improve this question

asked 14 hours ago

L XandorL Xandor

1386

$endgroup$

add a comment | 

1

$begingroup$

I have a DCGAN set up in tensorflow that is working well on the faces in the wild dataset. As an experiment, I tried using the same architecture in keras to better understand the difference in implementation. Performance so far is much worse in keras, but there are a few things I'm uncertain about how they translate, esp regularizer.

In tf, I apply the regularizer with

tf.contrib.layers.apply_regularization

Which is just applied to the whole network it seems. However in keras this must be specified in each layer, and there are three different kinds, kernel, bias and activity regularizer.

I'm trying to udnerstand how they differ, if tf regularizer applies one of the 3 keras types, and how to implement it the same way - do I call it in each convolutional layer including the final output layer? which of the 3 is equivalent of the default regularizer in tf?

Thanks

keras tensorflow convolution gan regularization

share|improve this question

asked 14 hours ago

L XandorL Xandor

1386

$endgroup$

add a comment | 

$begingroup$

I have a DCGAN set up in tensorflow that is working well on the faces in the wild dataset. As an experiment, I tried using the same architecture in keras to better understand the difference in implementation. Performance so far is much worse in keras, but there are a few things I'm uncertain about how they translate, esp regularizer.

In tf, I apply the regularizer with

tf.contrib.layers.apply_regularization

Which is just applied to the whole network it seems. However in keras this must be specified in each layer, and there are three different kinds, kernel, bias and activity regularizer.

I'm trying to udnerstand how they differ, if tf regularizer applies one of the 3 keras types, and how to implement it the same way - do I call it in each convolutional layer including the final output layer? which of the 3 is equivalent of the default regularizer in tf?

Thanks

keras tensorflow convolution gan regularization

share|improve this question

asked 14 hours ago

L XandorL Xandor

1386

$endgroup$

tf.contrib.layers.apply_regularization

share|improve this question

asked 14 hours ago

L XandorL Xandor

1386

share|improve this question

asked 14 hours ago

L XandorL Xandor

1386

asked 14 hours ago

L XandorL Xandor

1386

asked 14 hours ago

L XandorL Xandor

1386