How to do channel-wise incremental training of Deep Neural Network in Caffe framework?
$begingroup$
I read the idea of channel-wise incremental training from the paper: Runtime configurable deep neural networks for energy-accuracy trade-off (https://dl.acm.org/citation.cfm?id=2968458).
The idea is to train the network that starts with only a fraction of the channels enabled. e.g. 25% channels across all layers. Then train 50% of the channels while keeping the weights in the first 25% channels freeze. So, in the end, we can have multiple networks with different sizes inside one master network.
Since the paper didn't provide the technical details, I wonder if anyone could give me some idea how to implement this channel-wise incremental training in Caffe framework?
Thanks.
training
$endgroup$
migrated from ai.stackexchange.com yesterday
This question came from our site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment.
add a comment |
$begingroup$
I read the idea of channel-wise incremental training from the paper: Runtime configurable deep neural networks for energy-accuracy trade-off (https://dl.acm.org/citation.cfm?id=2968458).
The idea is to train the network that starts with only a fraction of the channels enabled. e.g. 25% channels across all layers. Then train 50% of the channels while keeping the weights in the first 25% channels freeze. So, in the end, we can have multiple networks with different sizes inside one master network.
Since the paper didn't provide the technical details, I wonder if anyone could give me some idea how to implement this channel-wise incremental training in Caffe framework?
Thanks.
training
$endgroup$
migrated from ai.stackexchange.com yesterday
This question came from our site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment.
add a comment |
$begingroup$
I read the idea of channel-wise incremental training from the paper: Runtime configurable deep neural networks for energy-accuracy trade-off (https://dl.acm.org/citation.cfm?id=2968458).
The idea is to train the network that starts with only a fraction of the channels enabled. e.g. 25% channels across all layers. Then train 50% of the channels while keeping the weights in the first 25% channels freeze. So, in the end, we can have multiple networks with different sizes inside one master network.
Since the paper didn't provide the technical details, I wonder if anyone could give me some idea how to implement this channel-wise incremental training in Caffe framework?
Thanks.
training
$endgroup$
I read the idea of channel-wise incremental training from the paper: Runtime configurable deep neural networks for energy-accuracy trade-off (https://dl.acm.org/citation.cfm?id=2968458).
The idea is to train the network that starts with only a fraction of the channels enabled. e.g. 25% channels across all layers. Then train 50% of the channels while keeping the weights in the first 25% channels freeze. So, in the end, we can have multiple networks with different sizes inside one master network.
Since the paper didn't provide the technical details, I wonder if anyone could give me some idea how to implement this channel-wise incremental training in Caffe framework?
Thanks.
training
training
asked Apr 9 at 17:33
Lei Xun
migrated from ai.stackexchange.com yesterday
This question came from our site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment.
migrated from ai.stackexchange.com yesterday
This question came from our site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment.
add a comment |
add a comment |
0
active
oldest
votes
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%2f49157%2fhow-to-do-channel-wise-incremental-training-of-deep-neural-network-in-caffe-fram%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
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%2f49157%2fhow-to-do-channel-wise-incremental-training-of-deep-neural-network-in-caffe-fram%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
