Mixing
Convolutional Neural Networks filter
When coding a convolutional neural network I am unsure of where to start with the convolutional layer. When different convolutional filters are used to produce different feature maps does that mean that the filters have different sizes (for example, 3x3, 2x2 etc.) ?
neural-network conv-neural-network
edited Nov 22 '18 at 6:15
vlizana
879315
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
add a comment |
When coding a convolutional neural network I am unsure of where to start with the convolutional layer. When different convolutional filters are used to produce different feature maps does that mean that the filters have different sizes (for example, 3x3, 2x2 etc.) ?
neural-network conv-neural-network
edited Nov 22 '18 at 6:15
vlizana
879315
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
add a comment |
When coding a convolutional neural network I am unsure of where to start with the convolutional layer. When different convolutional filters are used to produce different feature maps does that mean that the filters have different sizes (for example, 3x3, 2x2 etc.) ?
neural-network conv-neural-network
edited Nov 22 '18 at 6:15
vlizana
879315
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
When coding a convolutional neural network I am unsure of where to start with the convolutional layer. When different convolutional filters are used to produce different feature maps does that mean that the filters have different sizes (for example, 3x3, 2x2 etc.) ?
neural-network conv-neural-network
neural-network conv-neural-network
edited Nov 22 '18 at 6:15
vlizana
879315
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
edited Nov 22 '18 at 6:15
vlizana
879315
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
edited Nov 22 '18 at 6:15
vlizana
879315
edited Nov 22 '18 at 6:15
vlizana
879315
edited Nov 22 '18 at 6:15
vlizana
879315
879315
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
asked Nov 22 '18 at 4:17
Anish TiwariAnish Tiwari
45
45
add a comment |
add a comment |
3 Answers
3
active
oldest
votes
In most examples which is a good indication of how to go about coding a convolutional neural network, you will find to start with 1 convolutional layer and pass layer sizes, 3x3 window, input data features.
model.add(Conv2D(layer_size, (3,3), input_shape = x.shape[1:]))
The filter sizes usually only differ in the max pooling layer e.g 2x2.
model.add(MaxPooling2D(pool_size=(2,2)))
Layer sizes are usually selected from range layer_size = [32, 64,128] and you can do the same to experiment with different convolution_layers = [1,2,3]
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
add a comment |
More than an answer, kindly consider this as a comment. Filters applied can be (mostly are in prod env) of different sizes. I would suggest reading more on invariance, that along with an optimization algorithm (like Stochastic Gradient Descent) stops two filters from learning same feature (though some do learn same features as well).
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
add a comment |
I've never seen different kernel sizes for the filters in the same layer, although it is possible to do so, is not a default option the frameworks I have used. What makes filters yield different feature maps are the weights.
Along different layers different kernel sizes are used because the idea of the convolutional networks is to gradually reduce dimensionality through downsampling layers (max pooling for example), so in deep levels you have smaller feature maps and a smaller filter keeps it convolutional and less fully connected (having a kernel the same size as the image is equivalent to have a dense layer).
If you're starting with convolutionals I recommend you to play with this interactive visualization of a CNN, it helped me with a lot of concepts.
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
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: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
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%2fstackoverflow.com%2fquestions%2f53423833%2fconvolutional-neural-networks-filter%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
3 Answers
3
active
oldest
votes
3 Answers
3
active
oldest
votes
active
oldest
votes
active
oldest
votes
In most examples which is a good indication of how to go about coding a convolutional neural network, you will find to start with 1 convolutional layer and pass layer sizes, 3x3 window, input data features.
model.add(Conv2D(layer_size, (3,3), input_shape = x.shape[1:]))
The filter sizes usually only differ in the max pooling layer e.g 2x2.
model.add(MaxPooling2D(pool_size=(2,2)))
Layer sizes are usually selected from range layer_size = [32, 64,128] and you can do the same to experiment with different convolution_layers = [1,2,3]
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
add a comment |
In most examples which is a good indication of how to go about coding a convolutional neural network, you will find to start with 1 convolutional layer and pass layer sizes, 3x3 window, input data features.
model.add(Conv2D(layer_size, (3,3), input_shape = x.shape[1:]))
The filter sizes usually only differ in the max pooling layer e.g 2x2.
model.add(MaxPooling2D(pool_size=(2,2)))
Layer sizes are usually selected from range layer_size = [32, 64,128] and you can do the same to experiment with different convolution_layers = [1,2,3]
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
add a comment |
In most examples which is a good indication of how to go about coding a convolutional neural network, you will find to start with 1 convolutional layer and pass layer sizes, 3x3 window, input data features.
model.add(Conv2D(layer_size, (3,3), input_shape = x.shape[1:]))
The filter sizes usually only differ in the max pooling layer e.g 2x2.
model.add(MaxPooling2D(pool_size=(2,2)))
Layer sizes are usually selected from range layer_size = [32, 64,128] and you can do the same to experiment with different convolution_layers = [1,2,3]
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
In most examples which is a good indication of how to go about coding a convolutional neural network, you will find to start with 1 convolutional layer and pass layer sizes, 3x3 window, input data features.
model.add(Conv2D(layer_size, (3,3), input_shape = x.shape[1:]))
The filter sizes usually only differ in the max pooling layer e.g 2x2.
model.add(MaxPooling2D(pool_size=(2,2)))
Layer sizes are usually selected from range layer_size = [32, 64,128] and you can do the same to experiment with different convolution_layers = [1,2,3]
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
answered Nov 22 '18 at 4:33
SuleimanSuleiman
1251313
1251313
add a comment |
add a comment |
More than an answer, kindly consider this as a comment. Filters applied can be (mostly are in prod env) of different sizes. I would suggest reading more on invariance, that along with an optimization algorithm (like Stochastic Gradient Descent) stops two filters from learning same feature (though some do learn same features as well).
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
add a comment |
More than an answer, kindly consider this as a comment. Filters applied can be (mostly are in prod env) of different sizes. I would suggest reading more on invariance, that along with an optimization algorithm (like Stochastic Gradient Descent) stops two filters from learning same feature (though some do learn same features as well).
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
add a comment |
More than an answer, kindly consider this as a comment. Filters applied can be (mostly are in prod env) of different sizes. I would suggest reading more on invariance, that along with an optimization algorithm (like Stochastic Gradient Descent) stops two filters from learning same feature (though some do learn same features as well).
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
More than an answer, kindly consider this as a comment. Filters applied can be (mostly are in prod env) of different sizes. I would suggest reading more on invariance, that along with an optimization algorithm (like Stochastic Gradient Descent) stops two filters from learning same feature (though some do learn same features as well).
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
edited Nov 22 '18 at 4:34
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
answered Nov 22 '18 at 4:26
Random NerdRandom Nerd
1314
1314
add a comment |
add a comment |
I've never seen different kernel sizes for the filters in the same layer, although it is possible to do so, is not a default option the frameworks I have used. What makes filters yield different feature maps are the weights.
Along different layers different kernel sizes are used because the idea of the convolutional networks is to gradually reduce dimensionality through downsampling layers (max pooling for example), so in deep levels you have smaller feature maps and a smaller filter keeps it convolutional and less fully connected (having a kernel the same size as the image is equivalent to have a dense layer).
If you're starting with convolutionals I recommend you to play with this interactive visualization of a CNN, it helped me with a lot of concepts.
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
add a comment |
I've never seen different kernel sizes for the filters in the same layer, although it is possible to do so, is not a default option the frameworks I have used. What makes filters yield different feature maps are the weights.
Along different layers different kernel sizes are used because the idea of the convolutional networks is to gradually reduce dimensionality through downsampling layers (max pooling for example), so in deep levels you have smaller feature maps and a smaller filter keeps it convolutional and less fully connected (having a kernel the same size as the image is equivalent to have a dense layer).
If you're starting with convolutionals I recommend you to play with this interactive visualization of a CNN, it helped me with a lot of concepts.
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
add a comment |
I've never seen different kernel sizes for the filters in the same layer, although it is possible to do so, is not a default option the frameworks I have used. What makes filters yield different feature maps are the weights.
Along different layers different kernel sizes are used because the idea of the convolutional networks is to gradually reduce dimensionality through downsampling layers (max pooling for example), so in deep levels you have smaller feature maps and a smaller filter keeps it convolutional and less fully connected (having a kernel the same size as the image is equivalent to have a dense layer).
If you're starting with convolutionals I recommend you to play with this interactive visualization of a CNN, it helped me with a lot of concepts.
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
I've never seen different kernel sizes for the filters in the same layer, although it is possible to do so, is not a default option the frameworks I have used. What makes filters yield different feature maps are the weights.
Along different layers different kernel sizes are used because the idea of the convolutional networks is to gradually reduce dimensionality through downsampling layers (max pooling for example), so in deep levels you have smaller feature maps and a smaller filter keeps it convolutional and less fully connected (having a kernel the same size as the image is equivalent to have a dense layer).
If you're starting with convolutionals I recommend you to play with this interactive visualization of a CNN, it helped me with a lot of concepts.
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
answered Nov 22 '18 at 4:48
vlizanavlizana
879315
879315
add a comment |
add a comment |
Thanks for contributing an answer to Stack Overflow!
- 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.
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%2fstackoverflow.com%2fquestions%2f53423833%2fconvolutional-neural-networks-filter%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
