Mixing
How to access intermediate activations in TensorFlow Slim models?
I am working with the open source implementation of MobileNet v2 provided in TensorFlow Slim. I would like to access intermediate activations (layer outputs/inputs) within the network. I want to do this so that I can:
1) Analyze the statistical properties of these activations (such as sparsity)
2) Apply L1 regularization to these activations (not weights) by adding their L1 norm to the network's loss function as done in Yoshua Bengio's paper on the Relu
My question is: How I can I dump intermediate activations to a numpy array to evaluate sparsity, and how can I add the L1 norm of these activations to the cost function?
I have found this answer but as a TensorFlow beginner (I typically use PyTorch) I am unsure how to apply this to slim.learning.train and slim.evaluation.evaluate_once.
tensorflow
edited Nov 22 '18 at 6:59
Nima
1,48441625
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
add a comment |
I am working with the open source implementation of MobileNet v2 provided in TensorFlow Slim. I would like to access intermediate activations (layer outputs/inputs) within the network. I want to do this so that I can:
1) Analyze the statistical properties of these activations (such as sparsity)
2) Apply L1 regularization to these activations (not weights) by adding their L1 norm to the network's loss function as done in Yoshua Bengio's paper on the Relu
My question is: How I can I dump intermediate activations to a numpy array to evaluate sparsity, and how can I add the L1 norm of these activations to the cost function?
I have found this answer but as a TensorFlow beginner (I typically use PyTorch) I am unsure how to apply this to slim.learning.train and slim.evaluation.evaluate_once.
tensorflow
edited Nov 22 '18 at 6:59
Nima
1,48441625
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
add a comment |
I am working with the open source implementation of MobileNet v2 provided in TensorFlow Slim. I would like to access intermediate activations (layer outputs/inputs) within the network. I want to do this so that I can:
1) Analyze the statistical properties of these activations (such as sparsity)
2) Apply L1 regularization to these activations (not weights) by adding their L1 norm to the network's loss function as done in Yoshua Bengio's paper on the Relu
My question is: How I can I dump intermediate activations to a numpy array to evaluate sparsity, and how can I add the L1 norm of these activations to the cost function?
I have found this answer but as a TensorFlow beginner (I typically use PyTorch) I am unsure how to apply this to slim.learning.train and slim.evaluation.evaluate_once.
tensorflow
edited Nov 22 '18 at 6:59
Nima
1,48441625
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
I am working with the open source implementation of MobileNet v2 provided in TensorFlow Slim. I would like to access intermediate activations (layer outputs/inputs) within the network. I want to do this so that I can:
1) Analyze the statistical properties of these activations (such as sparsity)
2) Apply L1 regularization to these activations (not weights) by adding their L1 norm to the network's loss function as done in Yoshua Bengio's paper on the Relu
My question is: How I can I dump intermediate activations to a numpy array to evaluate sparsity, and how can I add the L1 norm of these activations to the cost function?
I have found this answer but as a TensorFlow beginner (I typically use PyTorch) I am unsure how to apply this to slim.learning.train and slim.evaluation.evaluate_once.
tensorflow
tensorflow
edited Nov 22 '18 at 6:59
Nima
1,48441625
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
edited Nov 22 '18 at 6:59
Nima
1,48441625
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
edited Nov 22 '18 at 6:59
Nima
1,48441625
edited Nov 22 '18 at 6:59
Nima
1,48441625
edited Nov 22 '18 at 6:59
Nima
1,48441625
1,48441625
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
asked Nov 19 '18 at 21:54
KantthpelKantthpel
697
697
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%2f53383187%2fhow-to-access-intermediate-activations-in-tensorflow-slim-models%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 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%2f53383187%2fhow-to-access-intermediate-activations-in-tensorflow-slim-models%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
