Encoder and decoder with different architectureTensorflow Autoencoder with 0 hidden units learns somethingAutoencoder - encoder vs decoder network size?Dimension Reduction in CLDNN (tensorflow)Tensorflow Autoencoder - How To Calculate Reconstruction Error?How to create an Autoencoder where the encoder/decoder weights are mirrored (transposed)LSTM Encoder and Decoder architecture for specific case in PytorchHow to enhance the performance of Mixed Autoencoder architecture?AutoEncoders not showing the expected output in kerasIs it valid to train the autoencoder before building the encoder/decoder models?
Do universities maintain secret textbooks?
How smart contract transactions work?
Can you use Apple Care+ without any checks (bringing just MacBook)?
What is the chance of getting a Red Cabbage in year 1?
Heuristic argument for the Riemann Hypothesis
How would a disabled person earn their living in a medieval-type town?
Using font to highlight a god's speech in dialogue
Who declared the Last Alliance to be the "last" and why?
apt-file regex: find multiple packages at once using or
Does the telecom provider need physical access to the SIM card to clone it?
IList<T> implementation
Private Domain and SAP
How can I improve my formal definitions?
How many possible file types in the output `ls -l` command?
Power supply circuit for a PIC16F88 Microchip
Ideas behind the 8.Bd3 line in the 4.Ng5 Two Knights Defense
Modeling an M1A2 Smoke Grenade Launcher
I was given someone else's visa, stamped in my passport
An idiom for “Until you punish the offender, they will not give up offenses”
What's the origin of the concept of alternate dimensions/realities?
Which is the correct version of Mussorgsky's Pictures at an Exhibition?
Heavy Box Stacking
Questions about Noun+が+Adjective
How to Calculate this definite integral or how to solve this series?
Encoder and decoder with different architecture
Tensorflow Autoencoder with 0 hidden units learns somethingAutoencoder - encoder vs decoder network size?Dimension Reduction in CLDNN (tensorflow)Tensorflow Autoencoder - How To Calculate Reconstruction Error?How to create an Autoencoder where the encoder/decoder weights are mirrored (transposed)LSTM Encoder and Decoder architecture for specific case in PytorchHow to enhance the performance of Mixed Autoencoder architecture?AutoEncoders not showing the expected output in kerasIs it valid to train the autoencoder before building the encoder/decoder models?
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;
I am using Variational autoencoder conditioned on some labels. I tried a lot of architectures, the one working the best (lowest loss) is the one were the decoder has three layers and the encoder has one layer.
In my sense adding the condition of labels as input to the decoder, makes the problem different from a simple compression/decompression scenario, and makes the decoder do a more complexe task to reconstruct the output.
It is right to use different encoderand decoder architecture in this case?
Thanks for you help,
conditional autoencoder
add a comment |
I am using Variational autoencoder conditioned on some labels. I tried a lot of architectures, the one working the best (lowest loss) is the one were the decoder has three layers and the encoder has one layer.
In my sense adding the condition of labels as input to the decoder, makes the problem different from a simple compression/decompression scenario, and makes the decoder do a more complexe task to reconstruct the output.
It is right to use different encoderand decoder architecture in this case?
Thanks for you help,
conditional autoencoder
add a comment |
I am using Variational autoencoder conditioned on some labels. I tried a lot of architectures, the one working the best (lowest loss) is the one were the decoder has three layers and the encoder has one layer.
In my sense adding the condition of labels as input to the decoder, makes the problem different from a simple compression/decompression scenario, and makes the decoder do a more complexe task to reconstruct the output.
It is right to use different encoderand decoder architecture in this case?
Thanks for you help,
conditional autoencoder
I am using Variational autoencoder conditioned on some labels. I tried a lot of architectures, the one working the best (lowest loss) is the one were the decoder has three layers and the encoder has one layer.
In my sense adding the condition of labels as input to the decoder, makes the problem different from a simple compression/decompression scenario, and makes the decoder do a more complexe task to reconstruct the output.
It is right to use different encoderand decoder architecture in this case?
Thanks for you help,
conditional autoencoder
conditional autoencoder
asked Mar 27 at 23:16
user2576975user2576975
304 bronze badges
304 bronze badges
add a comment |
add a comment |
0
active
oldest
votes
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%2f55387918%2fencoder-and-decoder-with-different-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
Is this question similar to what you get asked at work? Learn more about asking and sharing private information with your coworkers using Stack Overflow for Teams.
Is this question similar to what you get asked at work? Learn more about asking and sharing private information with your coworkers using Stack Overflow for Teams.
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%2f55387918%2fencoder-and-decoder-with-different-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