Cardinality vs width in the ResNext architecture
$begingroup$
I was recently reading the paper Aggregated Residual Transformations for Deep Neural Networks.
One thing the author mentions in Section (5.1) is that increasing the cardinality (or, the number of branches), decreases validation error more than increasing the bottleneck width or increasing the depth. I understand the depth part, but I'm a bit confused about the width. Isn't the cardinality of a residual block the same as the bottleneck width? If not, what is the difference?
Thanks!
neural-network deep-learning convolution
asked yesterday
JohnDoeJohnDoe
1011
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I was recently reading the paper Aggregated Residual Transformations for Deep Neural Networks.
One thing the author mentions in Section (5.1) is that increasing the cardinality (or, the number of branches), decreases validation error more than increasing the bottleneck width or increasing the depth. I understand the depth part, but I'm a bit confused about the width. Isn't the cardinality of a residual block the same as the bottleneck width? If not, what is the difference?
Thanks!
neural-network deep-learning convolution
asked yesterday
JohnDoeJohnDoe
1011
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I was recently reading the paper Aggregated Residual Transformations for Deep Neural Networks.
One thing the author mentions in Section (5.1) is that increasing the cardinality (or, the number of branches), decreases validation error more than increasing the bottleneck width or increasing the depth. I understand the depth part, but I'm a bit confused about the width. Isn't the cardinality of a residual block the same as the bottleneck width? If not, what is the difference?
Thanks!
neural-network deep-learning convolution
asked yesterday
JohnDoeJohnDoe
1011
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I was recently reading the paper Aggregated Residual Transformations for Deep Neural Networks.
One thing the author mentions in Section (5.1) is that increasing the cardinality (or, the number of branches), decreases validation error more than increasing the bottleneck width or increasing the depth. I understand the depth part, but I'm a bit confused about the width. Isn't the cardinality of a residual block the same as the bottleneck width? If not, what is the difference?
Thanks!
neural-network deep-learning convolution
neural-network deep-learning convolution
asked yesterday
JohnDoeJohnDoe
1011
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
JohnDoeJohnDoe
1011
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
JohnDoeJohnDoe
1011
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
JohnDoeJohnDoe
1011
asked yesterday
JohnDoeJohnDoe
1011
1011
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
JohnDoe is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
0
active
oldest
votes
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
});
}
});
JohnDoe is a new contributor. Be nice, and check out our Code of Conduct.
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%2f47559%2fcardinality-vs-width-in-the-resnext-architecture%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
JohnDoe is a new contributor. Be nice, and check out our Code of Conduct.
JohnDoe is a new contributor. Be nice, and check out our Code of Conduct.
JohnDoe is a new contributor. Be nice, and check out our Code of Conduct.
JohnDoe is a new contributor. Be nice, and check out our Code of Conduct.
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%2f47559%2fcardinality-vs-width-in-the-resnext-architecture%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
