What is the difference between Inception v2 and Inception v3?
$begingroup$
The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules:
The change to inception v2 was that they replaced the 5x5 convolutions by two successive 3x3 convolutions and applied pooling:
What is the difference between Inception v2 and Inception v3?
image-classification convnet computer-vision inception
$endgroup$
add a comment |
$begingroup$
The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules:
The change to inception v2 was that they replaced the 5x5 convolutions by two successive 3x3 convolutions and applied pooling:
What is the difference between Inception v2 and Inception v3?
image-classification convnet computer-vision inception
$endgroup$
$begingroup$
Is it simply batch normalization? Or does Inception v2 already have batch normalization?
$endgroup$
– Martin Thoma
Nov 24 '16 at 11:16
$begingroup$
github.com/SKKSaikia/CNN-GoogLeNet This repository holds all the versions of GoogLeNet and their difference. Give it a try.
$endgroup$
– Amartya Ranjan Saikia
Feb 13 '18 at 4:21
add a comment |
$begingroup$
The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules:
The change to inception v2 was that they replaced the 5x5 convolutions by two successive 3x3 convolutions and applied pooling:
What is the difference between Inception v2 and Inception v3?
image-classification convnet computer-vision inception
$endgroup$
The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules:
The change to inception v2 was that they replaced the 5x5 convolutions by two successive 3x3 convolutions and applied pooling:
What is the difference between Inception v2 and Inception v3?
image-classification convnet computer-vision inception
image-classification convnet computer-vision inception
asked Nov 24 '16 at 11:10
Martin ThomaMartin Thoma
6,0051353126
6,0051353126
$begingroup$
Is it simply batch normalization? Or does Inception v2 already have batch normalization?
$endgroup$
– Martin Thoma
Nov 24 '16 at 11:16
$begingroup$
github.com/SKKSaikia/CNN-GoogLeNet This repository holds all the versions of GoogLeNet and their difference. Give it a try.
$endgroup$
– Amartya Ranjan Saikia
Feb 13 '18 at 4:21
add a comment |
$begingroup$
Is it simply batch normalization? Or does Inception v2 already have batch normalization?
$endgroup$
– Martin Thoma
Nov 24 '16 at 11:16
$begingroup$
github.com/SKKSaikia/CNN-GoogLeNet This repository holds all the versions of GoogLeNet and their difference. Give it a try.
$endgroup$
– Amartya Ranjan Saikia
Feb 13 '18 at 4:21
$begingroup$
Is it simply batch normalization? Or does Inception v2 already have batch normalization?
$endgroup$
– Martin Thoma
Nov 24 '16 at 11:16
$begingroup$
Is it simply batch normalization? Or does Inception v2 already have batch normalization?
$endgroup$
– Martin Thoma
Nov 24 '16 at 11:16
$begingroup$
github.com/SKKSaikia/CNN-GoogLeNet This repository holds all the versions of GoogLeNet and their difference. Give it a try.
$endgroup$
– Amartya Ranjan Saikia
Feb 13 '18 at 4:21
$begingroup$
github.com/SKKSaikia/CNN-GoogLeNet This repository holds all the versions of GoogLeNet and their difference. Give it a try.
$endgroup$
– Amartya Ranjan Saikia
Feb 13 '18 at 4:21
add a comment |
4 Answers
4
active
oldest
votes
$begingroup$
In the paper Batch Normalization,Sergey et al,2015. proposed Inception-v1 architecture which is a variant of the GoogleNet in the paper Going deeper with convolutions, and in the meanwhile they introduced Batch Normalization to Inception(BN-Inception).
The main difference to the network described in (Szegedy et al.,2014)
is that the 5x5 convolutional layers are replaced by two consecutive
layer of 3x3 convolutions with up to 128 filters.
And in the paper Rethinking the Inception Architecture for Computer Vision, the authors proposed Inception-v2 and Inception-v3.
In the Inception-v2, they introduced Factorization(factorize convolutions into smaller convolutions) and some minor change into Inception-v1.
Note that we have factorized the traditional 7x7 convolution into
three 3x3 convolutions
As for Inception-v3, it is a variant of Inception-v2 which adds BN-auxiliary.
BN auxiliary refers to the version in which the fully connected layer of the auxiliary classifier is also-normalized, not just convolutions. We are refering to the model [Inception-v2 + BN auxiliary] as Inception-v3.
$endgroup$
add a comment |
$begingroup$
beside what was mentioned by daoliker
inception v2 utilized separable convolution as first layer of depth 64
- function usage
- function definition
- paper
quote from paper
Our model employed separable convolution with depth
multiplier 8 on the first convolutional layer. This reduces
the computational cost while increasing the memory consumption
at training time.
why this is important? because it was dropped in v3 and v4 and inception resnet, but re-introduced and heavily used in mobilenet later.
$endgroup$
add a comment |
$begingroup$
The answer can be found in the Going deeper with convolutions paper: https://arxiv.org/pdf/1512.00567v3.pdf
Check Table 3. Inception v2 is the architecture described in the Going deeper with convolutions paper. Inception v3 is the same architecture (minor changes) with different training algorithm (RMSprop, label smoothing regularizer, adding an auxiliary head with batch norm to improve training etc).
$endgroup$
add a comment |
$begingroup$
Actually, the answers above seem to be wrong. Indeed, it was a big mess with the naming. However, it seems that it was fixed in the paper that introduces Inception-v4 (see: "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning"):
The Inception deep convolutional architecture was introduced as GoogLeNet in (Szegedy et al. 2015a), here named Inception-v1. Later the Inception architecture was refined in various ways, first by the introduction of batch normalization (Ioffe and Szegedy 2015) (Inception-v2). Later by additional factorization ideas in the third iteration (Szegedy et al. 2015b) which will be referred to as Inception-v3 in this report.
New contributor
$endgroup$
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
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%2f15328%2fwhat-is-the-difference-between-inception-v2-and-inception-v3%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
4 Answers
4
active
oldest
votes
4 Answers
4
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
In the paper Batch Normalization,Sergey et al,2015. proposed Inception-v1 architecture which is a variant of the GoogleNet in the paper Going deeper with convolutions, and in the meanwhile they introduced Batch Normalization to Inception(BN-Inception).
The main difference to the network described in (Szegedy et al.,2014)
is that the 5x5 convolutional layers are replaced by two consecutive
layer of 3x3 convolutions with up to 128 filters.
And in the paper Rethinking the Inception Architecture for Computer Vision, the authors proposed Inception-v2 and Inception-v3.
In the Inception-v2, they introduced Factorization(factorize convolutions into smaller convolutions) and some minor change into Inception-v1.
Note that we have factorized the traditional 7x7 convolution into
three 3x3 convolutions
As for Inception-v3, it is a variant of Inception-v2 which adds BN-auxiliary.
BN auxiliary refers to the version in which the fully connected layer of the auxiliary classifier is also-normalized, not just convolutions. We are refering to the model [Inception-v2 + BN auxiliary] as Inception-v3.
$endgroup$
add a comment |
$begingroup$
In the paper Batch Normalization,Sergey et al,2015. proposed Inception-v1 architecture which is a variant of the GoogleNet in the paper Going deeper with convolutions, and in the meanwhile they introduced Batch Normalization to Inception(BN-Inception).
The main difference to the network described in (Szegedy et al.,2014)
is that the 5x5 convolutional layers are replaced by two consecutive
layer of 3x3 convolutions with up to 128 filters.
And in the paper Rethinking the Inception Architecture for Computer Vision, the authors proposed Inception-v2 and Inception-v3.
In the Inception-v2, they introduced Factorization(factorize convolutions into smaller convolutions) and some minor change into Inception-v1.
Note that we have factorized the traditional 7x7 convolution into
three 3x3 convolutions
As for Inception-v3, it is a variant of Inception-v2 which adds BN-auxiliary.
BN auxiliary refers to the version in which the fully connected layer of the auxiliary classifier is also-normalized, not just convolutions. We are refering to the model [Inception-v2 + BN auxiliary] as Inception-v3.
$endgroup$
add a comment |
$begingroup$
In the paper Batch Normalization,Sergey et al,2015. proposed Inception-v1 architecture which is a variant of the GoogleNet in the paper Going deeper with convolutions, and in the meanwhile they introduced Batch Normalization to Inception(BN-Inception).
The main difference to the network described in (Szegedy et al.,2014)
is that the 5x5 convolutional layers are replaced by two consecutive
layer of 3x3 convolutions with up to 128 filters.
And in the paper Rethinking the Inception Architecture for Computer Vision, the authors proposed Inception-v2 and Inception-v3.
In the Inception-v2, they introduced Factorization(factorize convolutions into smaller convolutions) and some minor change into Inception-v1.
Note that we have factorized the traditional 7x7 convolution into
three 3x3 convolutions
As for Inception-v3, it is a variant of Inception-v2 which adds BN-auxiliary.
BN auxiliary refers to the version in which the fully connected layer of the auxiliary classifier is also-normalized, not just convolutions. We are refering to the model [Inception-v2 + BN auxiliary] as Inception-v3.
$endgroup$
In the paper Batch Normalization,Sergey et al,2015. proposed Inception-v1 architecture which is a variant of the GoogleNet in the paper Going deeper with convolutions, and in the meanwhile they introduced Batch Normalization to Inception(BN-Inception).
The main difference to the network described in (Szegedy et al.,2014)
is that the 5x5 convolutional layers are replaced by two consecutive
layer of 3x3 convolutions with up to 128 filters.
And in the paper Rethinking the Inception Architecture for Computer Vision, the authors proposed Inception-v2 and Inception-v3.
In the Inception-v2, they introduced Factorization(factorize convolutions into smaller convolutions) and some minor change into Inception-v1.
Note that we have factorized the traditional 7x7 convolution into
three 3x3 convolutions
As for Inception-v3, it is a variant of Inception-v2 which adds BN-auxiliary.
BN auxiliary refers to the version in which the fully connected layer of the auxiliary classifier is also-normalized, not just convolutions. We are refering to the model [Inception-v2 + BN auxiliary] as Inception-v3.
edited Jun 28 '17 at 17:07
Muayyad Alsadi
1233
1233
answered Feb 21 '17 at 12:11
daolikerdaoliker
28125
28125
add a comment |
add a comment |
$begingroup$
beside what was mentioned by daoliker
inception v2 utilized separable convolution as first layer of depth 64
- function usage
- function definition
- paper
quote from paper
Our model employed separable convolution with depth
multiplier 8 on the first convolutional layer. This reduces
the computational cost while increasing the memory consumption
at training time.
why this is important? because it was dropped in v3 and v4 and inception resnet, but re-introduced and heavily used in mobilenet later.
$endgroup$
add a comment |
$begingroup$
beside what was mentioned by daoliker
inception v2 utilized separable convolution as first layer of depth 64
- function usage
- function definition
- paper
quote from paper
Our model employed separable convolution with depth
multiplier 8 on the first convolutional layer. This reduces
the computational cost while increasing the memory consumption
at training time.
why this is important? because it was dropped in v3 and v4 and inception resnet, but re-introduced and heavily used in mobilenet later.
$endgroup$
add a comment |
$begingroup$
beside what was mentioned by daoliker
inception v2 utilized separable convolution as first layer of depth 64
- function usage
- function definition
- paper
quote from paper
Our model employed separable convolution with depth
multiplier 8 on the first convolutional layer. This reduces
the computational cost while increasing the memory consumption
at training time.
why this is important? because it was dropped in v3 and v4 and inception resnet, but re-introduced and heavily used in mobilenet later.
$endgroup$
beside what was mentioned by daoliker
inception v2 utilized separable convolution as first layer of depth 64
- function usage
- function definition
- paper
quote from paper
Our model employed separable convolution with depth
multiplier 8 on the first convolutional layer. This reduces
the computational cost while increasing the memory consumption
at training time.
why this is important? because it was dropped in v3 and v4 and inception resnet, but re-introduced and heavily used in mobilenet later.
answered Jun 21 '17 at 22:40
Muayyad AlsadiMuayyad Alsadi
1233
1233
add a comment |
add a comment |
$begingroup$
The answer can be found in the Going deeper with convolutions paper: https://arxiv.org/pdf/1512.00567v3.pdf
Check Table 3. Inception v2 is the architecture described in the Going deeper with convolutions paper. Inception v3 is the same architecture (minor changes) with different training algorithm (RMSprop, label smoothing regularizer, adding an auxiliary head with batch norm to improve training etc).
$endgroup$
add a comment |
$begingroup$
The answer can be found in the Going deeper with convolutions paper: https://arxiv.org/pdf/1512.00567v3.pdf
Check Table 3. Inception v2 is the architecture described in the Going deeper with convolutions paper. Inception v3 is the same architecture (minor changes) with different training algorithm (RMSprop, label smoothing regularizer, adding an auxiliary head with batch norm to improve training etc).
$endgroup$
add a comment |
$begingroup$
The answer can be found in the Going deeper with convolutions paper: https://arxiv.org/pdf/1512.00567v3.pdf
Check Table 3. Inception v2 is the architecture described in the Going deeper with convolutions paper. Inception v3 is the same architecture (minor changes) with different training algorithm (RMSprop, label smoothing regularizer, adding an auxiliary head with batch norm to improve training etc).
$endgroup$
The answer can be found in the Going deeper with convolutions paper: https://arxiv.org/pdf/1512.00567v3.pdf
Check Table 3. Inception v2 is the architecture described in the Going deeper with convolutions paper. Inception v3 is the same architecture (minor changes) with different training algorithm (RMSprop, label smoothing regularizer, adding an auxiliary head with batch norm to improve training etc).
edited Jan 18 '17 at 4:50
answered Jan 18 '17 at 4:05
Sid MSid M
112
112
add a comment |
add a comment |
$begingroup$
Actually, the answers above seem to be wrong. Indeed, it was a big mess with the naming. However, it seems that it was fixed in the paper that introduces Inception-v4 (see: "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning"):
The Inception deep convolutional architecture was introduced as GoogLeNet in (Szegedy et al. 2015a), here named Inception-v1. Later the Inception architecture was refined in various ways, first by the introduction of batch normalization (Ioffe and Szegedy 2015) (Inception-v2). Later by additional factorization ideas in the third iteration (Szegedy et al. 2015b) which will be referred to as Inception-v3 in this report.
New contributor
$endgroup$
add a comment |
$begingroup$
Actually, the answers above seem to be wrong. Indeed, it was a big mess with the naming. However, it seems that it was fixed in the paper that introduces Inception-v4 (see: "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning"):
The Inception deep convolutional architecture was introduced as GoogLeNet in (Szegedy et al. 2015a), here named Inception-v1. Later the Inception architecture was refined in various ways, first by the introduction of batch normalization (Ioffe and Szegedy 2015) (Inception-v2). Later by additional factorization ideas in the third iteration (Szegedy et al. 2015b) which will be referred to as Inception-v3 in this report.
New contributor
$endgroup$
add a comment |
$begingroup$
Actually, the answers above seem to be wrong. Indeed, it was a big mess with the naming. However, it seems that it was fixed in the paper that introduces Inception-v4 (see: "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning"):
The Inception deep convolutional architecture was introduced as GoogLeNet in (Szegedy et al. 2015a), here named Inception-v1. Later the Inception architecture was refined in various ways, first by the introduction of batch normalization (Ioffe and Szegedy 2015) (Inception-v2). Later by additional factorization ideas in the third iteration (Szegedy et al. 2015b) which will be referred to as Inception-v3 in this report.
New contributor
$endgroup$
Actually, the answers above seem to be wrong. Indeed, it was a big mess with the naming. However, it seems that it was fixed in the paper that introduces Inception-v4 (see: "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning"):
The Inception deep convolutional architecture was introduced as GoogLeNet in (Szegedy et al. 2015a), here named Inception-v1. Later the Inception architecture was refined in various ways, first by the introduction of batch normalization (Ioffe and Szegedy 2015) (Inception-v2). Later by additional factorization ideas in the third iteration (Szegedy et al. 2015b) which will be referred to as Inception-v3 in this report.
New contributor
New contributor
answered 50 mins ago
desadesa
101
101
New contributor
New contributor
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%2f15328%2fwhat-is-the-difference-between-inception-v2-and-inception-v3%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
$begingroup$
Is it simply batch normalization? Or does Inception v2 already have batch normalization?
$endgroup$
– Martin Thoma
Nov 24 '16 at 11:16
$begingroup$
github.com/SKKSaikia/CNN-GoogLeNet This repository holds all the versions of GoogLeNet and their difference. Give it a try.
$endgroup$
– Amartya Ranjan Saikia
Feb 13 '18 at 4:21