What is the best architecture for Auto-Encoder for image reconstruction?
$begingroup$
I am trying to use Convultional Auto-Encoder for its latent space (embedding layer), specifically, I want to use the embedding for K-nearest neighbor search in the latent space (similar idea to word2vec).
My input is 224x224 (ImageNet). I could not find any article that elaborates a specific architecture (in terms of number of filters, number of conv layers, etc.)
I tried some arbitrary architectures like:
Encoder:
- Conv(channels=3,filters=16,kernel=3)
- Conv(channels=16,filters=32,kernel=3)
- Conv(channels=32,filters=64,kernel=3)
Decoder:
- Conv(channels=64,filters=32,kernel=3)
- Conv(channels=32,filters=16,kernel=3)
- Conv(channels=16,filters=3,kernel=3)
But I'd like to start my hyper-parameters search from a set up that proved itself on a similar task.
Can you refer me to a source or suggest an architecture that worked for you for this purpose?
neural-network deep-learning convnet autoencoder
edited 16 mins ago
Stephen Rauch♦
1,52551330
asked yesterday
Idan azuriIdan azuri
62
New contributor
Idan azuri 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 am trying to use Convultional Auto-Encoder for its latent space (embedding layer), specifically, I want to use the embedding for K-nearest neighbor search in the latent space (similar idea to word2vec).
My input is 224x224 (ImageNet). I could not find any article that elaborates a specific architecture (in terms of number of filters, number of conv layers, etc.)
I tried some arbitrary architectures like:
Encoder:
- Conv(channels=3,filters=16,kernel=3)
- Conv(channels=16,filters=32,kernel=3)
- Conv(channels=32,filters=64,kernel=3)
Decoder:
- Conv(channels=64,filters=32,kernel=3)
- Conv(channels=32,filters=16,kernel=3)
- Conv(channels=16,filters=3,kernel=3)
But I'd like to start my hyper-parameters search from a set up that proved itself on a similar task.
Can you refer me to a source or suggest an architecture that worked for you for this purpose?
neural-network deep-learning convnet autoencoder
edited 16 mins ago
Stephen Rauch♦
1,52551330
asked yesterday
Idan azuriIdan azuri
62
New contributor
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
$begingroup$
There is none. You should always optimize your network through an "ad hoc" hyperparameter search that depends on the problem at hand.
$endgroup$
– pcko1
yesterday
$begingroup$
@pcko1 disagree, in many cases, it is very helpful to use a similar problem architecture and then to make the fine-tuning. Moreover, my dataset is ImageNet which is very investigated. Last, until you didn't cover all the articles in arxiv you can't say "there is none"...
$endgroup$
– Idan azuri
yesterday
add a comment |
$begingroup$
I am trying to use Convultional Auto-Encoder for its latent space (embedding layer), specifically, I want to use the embedding for K-nearest neighbor search in the latent space (similar idea to word2vec).
My input is 224x224 (ImageNet). I could not find any article that elaborates a specific architecture (in terms of number of filters, number of conv layers, etc.)
I tried some arbitrary architectures like:
Encoder:
- Conv(channels=3,filters=16,kernel=3)
- Conv(channels=16,filters=32,kernel=3)
- Conv(channels=32,filters=64,kernel=3)
Decoder:
- Conv(channels=64,filters=32,kernel=3)
- Conv(channels=32,filters=16,kernel=3)
- Conv(channels=16,filters=3,kernel=3)
But I'd like to start my hyper-parameters search from a set up that proved itself on a similar task.
Can you refer me to a source or suggest an architecture that worked for you for this purpose?
neural-network deep-learning convnet autoencoder
edited 16 mins ago
Stephen Rauch♦
1,52551330
asked yesterday
Idan azuriIdan azuri
62
New contributor
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I am trying to use Convultional Auto-Encoder for its latent space (embedding layer), specifically, I want to use the embedding for K-nearest neighbor search in the latent space (similar idea to word2vec).
My input is 224x224 (ImageNet). I could not find any article that elaborates a specific architecture (in terms of number of filters, number of conv layers, etc.)
I tried some arbitrary architectures like:
Encoder:
- Conv(channels=3,filters=16,kernel=3)
- Conv(channels=16,filters=32,kernel=3)
- Conv(channels=32,filters=64,kernel=3)
Decoder:
- Conv(channels=64,filters=32,kernel=3)
- Conv(channels=32,filters=16,kernel=3)
- Conv(channels=16,filters=3,kernel=3)
But I'd like to start my hyper-parameters search from a set up that proved itself on a similar task.
Can you refer me to a source or suggest an architecture that worked for you for this purpose?
neural-network deep-learning convnet autoencoder
neural-network deep-learning convnet autoencoder
edited 16 mins ago
Stephen Rauch♦
1,52551330
asked yesterday
Idan azuriIdan azuri
62
New contributor
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
edited 16 mins ago
Stephen Rauch♦
1,52551330
asked yesterday
Idan azuriIdan azuri
62
New contributor
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
edited 16 mins ago
Stephen Rauch♦
1,52551330
edited 16 mins ago
Stephen Rauch♦
1,52551330
edited 16 mins ago
Stephen Rauch♦
1,52551330
1,52551330
asked yesterday
Idan azuriIdan azuri
62
New contributor
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
Idan azuriIdan azuri
62
asked yesterday
Idan azuriIdan azuri
62
62
New contributor
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Idan azuri is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$begingroup$
There is none. You should always optimize your network through an "ad hoc" hyperparameter search that depends on the problem at hand.
$endgroup$
– pcko1
yesterday
$begingroup$
@pcko1 disagree, in many cases, it is very helpful to use a similar problem architecture and then to make the fine-tuning. Moreover, my dataset is ImageNet which is very investigated. Last, until you didn't cover all the articles in arxiv you can't say "there is none"...
$endgroup$
– Idan azuri
yesterday
add a comment |
$begingroup$
There is none. You should always optimize your network through an "ad hoc" hyperparameter search that depends on the problem at hand.
$endgroup$
– pcko1
yesterday
$begingroup$
@pcko1 disagree, in many cases, it is very helpful to use a similar problem architecture and then to make the fine-tuning. Moreover, my dataset is ImageNet which is very investigated. Last, until you didn't cover all the articles in arxiv you can't say "there is none"...
$endgroup$
– Idan azuri
yesterday
$begingroup$
There is none. You should always optimize your network through an "ad hoc" hyperparameter search that depends on the problem at hand.
$endgroup$
– pcko1
yesterday
$begingroup$
There is none. You should always optimize your network through an "ad hoc" hyperparameter search that depends on the problem at hand.
$endgroup$
– pcko1
yesterday
$begingroup$
@pcko1 disagree, in many cases, it is very helpful to use a similar problem architecture and then to make the fine-tuning. Moreover, my dataset is ImageNet which is very investigated. Last, until you didn't cover all the articles in arxiv you can't say "there is none"...
$endgroup$
– Idan azuri
yesterday
$begingroup$
@pcko1 disagree, in many cases, it is very helpful to use a similar problem architecture and then to make the fine-tuning. Moreover, my dataset is ImageNet which is very investigated. Last, until you didn't cover all the articles in arxiv you can't say "there is none"...
$endgroup$
– Idan azuri
yesterday
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
});
}
});
Idan azuri 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%2f49709%2fwhat-is-the-best-architecture-for-auto-encoder-for-image-reconstruction%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
Idan azuri is a new contributor. Be nice, and check out our Code of Conduct.
Idan azuri is a new contributor. Be nice, and check out our Code of Conduct.
Idan azuri is a new contributor. Be nice, and check out our Code of Conduct.
Idan azuri 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%2f49709%2fwhat-is-the-best-architecture-for-auto-encoder-for-image-reconstruction%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
$begingroup$
There is none. You should always optimize your network through an "ad hoc" hyperparameter search that depends on the problem at hand.
$endgroup$
– pcko1
yesterday
$begingroup$
@pcko1 disagree, in many cases, it is very helpful to use a similar problem architecture and then to make the fine-tuning. Moreover, my dataset is ImageNet which is very investigated. Last, until you didn't cover all the articles in arxiv you can't say "there is none"...
$endgroup$
– Idan azuri
yesterday