Adding batch normalization layer to VGG16 network The 2019 Stack Overflow Developer Survey Results Are In Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern) 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsConvolutional neural network overfitting. Dropout not helpingNeural network for peak identification problem not training successfullyFinal layer of neural network responsible for overfittingHow to make output dimensions match input dimensions in CNN?Reshape output of convolutional layer to which dimensions?Visualizing ConvNet filters using my own fine-tuned network resulting in a “NoneType” when running: K.gradients(loss, model.input)[0]Custom loss function which is included gradient in KerasValue of loss and accuracy does not change over EpochsMultiple-input multiple-output CNN with custom loss functionUnderstanding LSTM structure
First use of “packing” as in carrying a gun
Am I ethically obligated to go into work on an off day if the reason is sudden?
Would it be possible to rearrange a dragon's flight muscle to somewhat circumvent the square-cube law?
What is special about square numbers here?
Create an outline of font
How do you keep chess fun when your opponent constantly beats you?
A pet rabbit called Belle
Does Parliament hold absolute power in the UK?
What aspect of planet Earth must be changed to prevent the industrial revolution?
Difference between "generating set" and free product?
How do I add random spotting to the same face in cycles?
Keeping a retro style to sci-fi spaceships?
Can the DM override racial traits?
Are my PIs rude or am I just being too sensitive?
Did the new image of black hole confirm the general theory of relativity?
How should I replace vector<uint8_t>::const_iterator in an API?
Can withdrawing asylum be illegal?
Can smartphones with the same camera sensor have different image quality?
Did God make two great lights or did He make the great light two?
Is it ethical to upload a automatically generated paper to a non peer-reviewed site as part of a larger research?
Relations between two reciprocal partial derivatives?
How to test the equality of two Pearson correlation coefficients computed from the same sample?
How are presidential pardons supposed to be used?
He got a vote 80% that of Emmanuel Macron’s
Adding batch normalization layer to VGG16 network
The 2019 Stack Overflow Developer Survey Results Are In
Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern)
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsConvolutional neural network overfitting. Dropout not helpingNeural network for peak identification problem not training successfullyFinal layer of neural network responsible for overfittingHow to make output dimensions match input dimensions in CNN?Reshape output of convolutional layer to which dimensions?Visualizing ConvNet filters using my own fine-tuned network resulting in a “NoneType” when running: K.gradients(loss, model.input)[0]Custom loss function which is included gradient in KerasValue of loss and accuracy does not change over EpochsMultiple-input multiple-output CNN with custom loss functionUnderstanding LSTM structure
$begingroup$
I want to use batch normalization layer to decrease overfitting in VGG16 CNN.
Where should the batch normalization layer be added to the network?
`_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
fc1 (Dense) (None, 4096) 102764544
_________________________________________________________________
fc2 (Dense) (None, 4096) 16781312
_________________________________________________________________
predictions (Dense) (None, 1000) 4097000
=================================================================`
machine-learning neural-network deep-learning keras cnn
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
$endgroup$
bumped to the homepage by Community♦ 31 mins ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
$begingroup$
I want to use batch normalization layer to decrease overfitting in VGG16 CNN.
Where should the batch normalization layer be added to the network?
`_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
fc1 (Dense) (None, 4096) 102764544
_________________________________________________________________
fc2 (Dense) (None, 4096) 16781312
_________________________________________________________________
predictions (Dense) (None, 1000) 4097000
=================================================================`
machine-learning neural-network deep-learning keras cnn
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
$endgroup$
bumped to the homepage by Community♦ 31 mins ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
$begingroup$
I want to use batch normalization layer to decrease overfitting in VGG16 CNN.
Where should the batch normalization layer be added to the network?
`_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
fc1 (Dense) (None, 4096) 102764544
_________________________________________________________________
fc2 (Dense) (None, 4096) 16781312
_________________________________________________________________
predictions (Dense) (None, 1000) 4097000
=================================================================`
machine-learning neural-network deep-learning keras cnn
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
$endgroup$
I want to use batch normalization layer to decrease overfitting in VGG16 CNN.
Where should the batch normalization layer be added to the network?
`_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
fc1 (Dense) (None, 4096) 102764544
_________________________________________________________________
fc2 (Dense) (None, 4096) 16781312
_________________________________________________________________
predictions (Dense) (None, 1000) 4097000
=================================================================`
machine-learning neural-network deep-learning keras cnn
machine-learning neural-network deep-learning keras cnn
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
edited Sep 13 '18 at 15:38
Vaalizaadeh
7,58562263
7,58562263
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
asked Sep 6 '18 at 14:31
N.ITN.IT
473112
473112
bumped to the homepage by Community♦ 31 mins ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
bumped to the homepage by Community♦ 31 mins ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
The main purpose of batch normalisation is not for dealing with overfitting but if you have small batches while training it can have regularization effect. In the paper that it was introduced for dealing with covariat shift, it was mentioned that it should be used before activation function. Consequently, you can use it both in convolutional layers and dense layers, after employing weights and before activation functions. But I've seen people using that after activation function. It can also be used there.
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
$endgroup$
add a comment |
Your Answer
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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
);
);
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
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f37889%2fadding-batch-normalization-layer-to-vgg16-network%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
The main purpose of batch normalisation is not for dealing with overfitting but if you have small batches while training it can have regularization effect. In the paper that it was introduced for dealing with covariat shift, it was mentioned that it should be used before activation function. Consequently, you can use it both in convolutional layers and dense layers, after employing weights and before activation functions. But I've seen people using that after activation function. It can also be used there.
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
$endgroup$
add a comment |
$begingroup$
The main purpose of batch normalisation is not for dealing with overfitting but if you have small batches while training it can have regularization effect. In the paper that it was introduced for dealing with covariat shift, it was mentioned that it should be used before activation function. Consequently, you can use it both in convolutional layers and dense layers, after employing weights and before activation functions. But I've seen people using that after activation function. It can also be used there.
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
$endgroup$
add a comment |
$begingroup$
The main purpose of batch normalisation is not for dealing with overfitting but if you have small batches while training it can have regularization effect. In the paper that it was introduced for dealing with covariat shift, it was mentioned that it should be used before activation function. Consequently, you can use it both in convolutional layers and dense layers, after employing weights and before activation functions. But I've seen people using that after activation function. It can also be used there.
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
$endgroup$
The main purpose of batch normalisation is not for dealing with overfitting but if you have small batches while training it can have regularization effect. In the paper that it was introduced for dealing with covariat shift, it was mentioned that it should be used before activation function. Consequently, you can use it both in convolutional layers and dense layers, after employing weights and before activation functions. But I've seen people using that after activation function. It can also be used there.
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
answered Sep 13 '18 at 15:38
VaalizaadehVaalizaadeh
7,58562263
7,58562263
add a comment |
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
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
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f37889%2fadding-batch-normalization-layer-to-vgg16-network%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
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
Required, but never shown
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
Required, but never shown
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
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
