How can I visualize deconvolution layer's output of shape=5,100,100,3 (in NHWC format) in tensorflow?
I'm trying to visualize the output of a deconvolutional layer in tensorflow. The shape of my layer is (5,100,100,3) in NHWC format. I'm trying to implement this concept to visualize all the 3 output channels in image format. But I'm unable to implement the concept written hereand I'm getting a Value error. Is there any code to visualize deconvolution layer output? I'm using tensorflow version 0.12 so cannot use Keras. The below code Ref. which I'm trying to implement in my case. Thanks in advance.
W1_a = W1 # [5, 5, 1, 24]
W1pad= tf.zeros([5, 5, 1, 1]) # [5, 5, 1, 1]
W1_b = tf.concat(3, [W1_a, W1pad]) # [5, 5, 1, 25]
W1_c = tf.split(3, 25, W1_b) # 25 x [5, 5, 1, 1]
W1_row0 = tf.concat(0, W1_c[0:5]) # [25, 5, 1, 1]
W1_row1 = tf.concat(0, W1_c[5:10]) # [25, 5, 1, 1]
W1_row2 = tf.concat(0, W1_c[10:15]) # [25, 5, 1, 1]
W1_row3 = tf.concat(0, W1_c[15:20]) # [25, 5, 1, 1]
W1_row4 = tf.concat(0, W1_c[20:25]) # [25, 5, 1, 1]
W1_d = tf.concat(1, [W1_row0, W1_row1, W1_row2, W1_row3, W1_row4]) # [25, 25, 1, 1]
W1_e = tf.reshape(W1_d, [1, 25, 25, 1])
Wtag = tf.placeholder(tf.string, None)
tf.image_summary(Wtag, W1_e)
python-2.7 tensorflow tensorboard
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
add a comment |
I'm trying to visualize the output of a deconvolutional layer in tensorflow. The shape of my layer is (5,100,100,3) in NHWC format. I'm trying to implement this concept to visualize all the 3 output channels in image format. But I'm unable to implement the concept written hereand I'm getting a Value error. Is there any code to visualize deconvolution layer output? I'm using tensorflow version 0.12 so cannot use Keras. The below code Ref. which I'm trying to implement in my case. Thanks in advance.
W1_a = W1 # [5, 5, 1, 24]
W1pad= tf.zeros([5, 5, 1, 1]) # [5, 5, 1, 1]
W1_b = tf.concat(3, [W1_a, W1pad]) # [5, 5, 1, 25]
W1_c = tf.split(3, 25, W1_b) # 25 x [5, 5, 1, 1]
W1_row0 = tf.concat(0, W1_c[0:5]) # [25, 5, 1, 1]
W1_row1 = tf.concat(0, W1_c[5:10]) # [25, 5, 1, 1]
W1_row2 = tf.concat(0, W1_c[10:15]) # [25, 5, 1, 1]
W1_row3 = tf.concat(0, W1_c[15:20]) # [25, 5, 1, 1]
W1_row4 = tf.concat(0, W1_c[20:25]) # [25, 5, 1, 1]
W1_d = tf.concat(1, [W1_row0, W1_row1, W1_row2, W1_row3, W1_row4]) # [25, 25, 1, 1]
W1_e = tf.reshape(W1_d, [1, 25, 25, 1])
Wtag = tf.placeholder(tf.string, None)
tf.image_summary(Wtag, W1_e)
python-2.7 tensorflow tensorboard
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
add a comment |
I'm trying to visualize the output of a deconvolutional layer in tensorflow. The shape of my layer is (5,100,100,3) in NHWC format. I'm trying to implement this concept to visualize all the 3 output channels in image format. But I'm unable to implement the concept written hereand I'm getting a Value error. Is there any code to visualize deconvolution layer output? I'm using tensorflow version 0.12 so cannot use Keras. The below code Ref. which I'm trying to implement in my case. Thanks in advance.
W1_a = W1 # [5, 5, 1, 24]
W1pad= tf.zeros([5, 5, 1, 1]) # [5, 5, 1, 1]
W1_b = tf.concat(3, [W1_a, W1pad]) # [5, 5, 1, 25]
W1_c = tf.split(3, 25, W1_b) # 25 x [5, 5, 1, 1]
W1_row0 = tf.concat(0, W1_c[0:5]) # [25, 5, 1, 1]
W1_row1 = tf.concat(0, W1_c[5:10]) # [25, 5, 1, 1]
W1_row2 = tf.concat(0, W1_c[10:15]) # [25, 5, 1, 1]
W1_row3 = tf.concat(0, W1_c[15:20]) # [25, 5, 1, 1]
W1_row4 = tf.concat(0, W1_c[20:25]) # [25, 5, 1, 1]
W1_d = tf.concat(1, [W1_row0, W1_row1, W1_row2, W1_row3, W1_row4]) # [25, 25, 1, 1]
W1_e = tf.reshape(W1_d, [1, 25, 25, 1])
Wtag = tf.placeholder(tf.string, None)
tf.image_summary(Wtag, W1_e)
python-2.7 tensorflow tensorboard
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
I'm trying to visualize the output of a deconvolutional layer in tensorflow. The shape of my layer is (5,100,100,3) in NHWC format. I'm trying to implement this concept to visualize all the 3 output channels in image format. But I'm unable to implement the concept written hereand I'm getting a Value error. Is there any code to visualize deconvolution layer output? I'm using tensorflow version 0.12 so cannot use Keras. The below code Ref. which I'm trying to implement in my case. Thanks in advance.
W1_a = W1 # [5, 5, 1, 24]
W1pad= tf.zeros([5, 5, 1, 1]) # [5, 5, 1, 1]
W1_b = tf.concat(3, [W1_a, W1pad]) # [5, 5, 1, 25]
W1_c = tf.split(3, 25, W1_b) # 25 x [5, 5, 1, 1]
W1_row0 = tf.concat(0, W1_c[0:5]) # [25, 5, 1, 1]
W1_row1 = tf.concat(0, W1_c[5:10]) # [25, 5, 1, 1]
W1_row2 = tf.concat(0, W1_c[10:15]) # [25, 5, 1, 1]
W1_row3 = tf.concat(0, W1_c[15:20]) # [25, 5, 1, 1]
W1_row4 = tf.concat(0, W1_c[20:25]) # [25, 5, 1, 1]
W1_d = tf.concat(1, [W1_row0, W1_row1, W1_row2, W1_row3, W1_row4]) # [25, 25, 1, 1]
W1_e = tf.reshape(W1_d, [1, 25, 25, 1])
Wtag = tf.placeholder(tf.string, None)
tf.image_summary(Wtag, W1_e)
python-2.7 tensorflow tensorboard
python-2.7 tensorflow tensorboard
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
asked Nov 19 '18 at 17:35
user1410665user1410665
2710
2710
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%2f53379934%2fhow-can-i-visualize-deconvolution-layers-output-of-shape-5-100-100-3-in-nhwc-f%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%2f53379934%2fhow-can-i-visualize-deconvolution-layers-output-of-shape-5-100-100-3-in-nhwc-f%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
