How to change self.kernel matrix of tensorflow CudaLstm cell during training?Tensorflow: how to save/restore a model?how to include stateful operation in your tensorflow graph?How do I share weights across different RNN cells that feed in different inputs in Tensorflow?Tensorflow - training weights via GD by handHow to avoid dying weights/gradients in custom LSTM cell in tensorflow. What shall be ideal loss function?Tensorflow: How do the gradients get incorporated into the trainable variables?how to create gradient function for tf.bincount in tensorflowAccess the weight matrix in Tensorflow in order to make apply changes to it in NumpyVariational Dropout in Kerashow to use a tensor instead of variable for the weights and biases in LSTM cells
Simple image editor tool to draw a simple box/rectangle in an existing image
Are taller landing gear bad for aircraft, particulary large airliners?
What is the term when two people sing in harmony, but they aren't singing the same notes?
Giant Toughroad SLR 2 for 200 miles in two days, will it make it?
Stereotypical names
How can I raise concerns with a new DM about XP splitting?
Is there enough fresh water in the world to eradicate the drinking water crisis?
Simple recursive Sudoku solver
Calculating the number of days between 2 dates in Excel
Can a Bard use an arcane focus?
Installing PowerShell on 32-bit Kali OS fails
Java - What do constructor type arguments mean when placed *before* the type?
Could solar power be utilized and substitute coal in the 19th century?
How to prevent YouTube from showing already watched videos?
Can I rely on these GitHub repository files?
Blender - show edges angles “direction”
Why isn't KTEX's runway designation 10/28 instead of 9/27?
I2C signal and power over long range (10meter cable)
Who must act to prevent Brexit on March 29th?
What to do when my ideas aren't chosen, when I strongly disagree with the chosen solution?
What do you call the infoboxes with text and sometimes images on the side of a page we find in textbooks?
Bob has never been a M before
Meta programming: Declare a new struct on the fly
Can a malicious addon access internet history and such in chrome/firefox?
How to change self.kernel matrix of tensorflow CudaLstm cell during training?
Tensorflow: how to save/restore a model?how to include stateful operation in your tensorflow graph?How do I share weights across different RNN cells that feed in different inputs in Tensorflow?Tensorflow - training weights via GD by handHow to avoid dying weights/gradients in custom LSTM cell in tensorflow. What shall be ideal loss function?Tensorflow: How do the gradients get incorporated into the trainable variables?how to create gradient function for tf.bincount in tensorflowAccess the weight matrix in Tensorflow in order to make apply changes to it in NumpyVariational Dropout in Kerashow to use a tensor instead of variable for the weights and biases in LSTM cells
I am trying to implement Dropconnect(weight dropout) on hidden-hidden weights of CudaLSTM cell in tensorflow. But I am unable to assign changed weight after dropout to self.kernel. Tensorflow provides canonicaltoparams and paramstocanonical method in tensorflow to convert tensorflow weights in optimized format. I am able to implement Dropconnect in basic/block LSTM cell but unable to figure out way to implement the same in CudaLSTM cell due to problem in direct accessing of LSTM weights. I am getting error" No gradient defined for operation CudnnRNNCanonicalToParams " (op type: CidnnRNNCanonicalToParams)
tensorflow
asked Mar 7 at 10:20
user3253409user3253409
12
add a comment |
I am trying to implement Dropconnect(weight dropout) on hidden-hidden weights of CudaLSTM cell in tensorflow. But I am unable to assign changed weight after dropout to self.kernel. Tensorflow provides canonicaltoparams and paramstocanonical method in tensorflow to convert tensorflow weights in optimized format. I am able to implement Dropconnect in basic/block LSTM cell but unable to figure out way to implement the same in CudaLSTM cell due to problem in direct accessing of LSTM weights. I am getting error" No gradient defined for operation CudnnRNNCanonicalToParams " (op type: CidnnRNNCanonicalToParams)
tensorflow
asked Mar 7 at 10:20
user3253409user3253409
12
add a comment |
I am trying to implement Dropconnect(weight dropout) on hidden-hidden weights of CudaLSTM cell in tensorflow. But I am unable to assign changed weight after dropout to self.kernel. Tensorflow provides canonicaltoparams and paramstocanonical method in tensorflow to convert tensorflow weights in optimized format. I am able to implement Dropconnect in basic/block LSTM cell but unable to figure out way to implement the same in CudaLSTM cell due to problem in direct accessing of LSTM weights. I am getting error" No gradient defined for operation CudnnRNNCanonicalToParams " (op type: CidnnRNNCanonicalToParams)
tensorflow
asked Mar 7 at 10:20
user3253409user3253409
12
I am trying to implement Dropconnect(weight dropout) on hidden-hidden weights of CudaLSTM cell in tensorflow. But I am unable to assign changed weight after dropout to self.kernel. Tensorflow provides canonicaltoparams and paramstocanonical method in tensorflow to convert tensorflow weights in optimized format. I am able to implement Dropconnect in basic/block LSTM cell but unable to figure out way to implement the same in CudaLSTM cell due to problem in direct accessing of LSTM weights. I am getting error" No gradient defined for operation CudnnRNNCanonicalToParams " (op type: CidnnRNNCanonicalToParams)
tensorflow
tensorflow
asked Mar 7 at 10:20
user3253409user3253409
12
asked Mar 7 at 10:20
user3253409user3253409
12
asked Mar 7 at 10:20
user3253409user3253409
12
asked Mar 7 at 10:20
user3253409user3253409
12
asked Mar 7 at 10:20
user3253409user3253409
12
12
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%2f55041350%2fhow-to-change-self-kernel-matrix-of-tensorflow-cudalstm-cell-during-training%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%2f55041350%2fhow-to-change-self-kernel-matrix-of-tensorflow-cudalstm-cell-during-training%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
