Tensorflow matmul how to deal with channel=None
up vote
0
down vote
favorite
I am trying to do matmul of two tensors, one is [None, 4, 256], and the other is its transpose (I use tf.transpose and got a tensor [256, 4, None]). The expected result is a [4, 4] tensor. When I use matmul, it returns an error. I am wondering, how can I get the expected result? Thank you!
#inputs: [None, 4, 256]
inputs_transpose = tf.transpose(inputs, perm = [0, 2, 1]) #[None, 256, 4]
temp_weights = tf.matmul(inputs, inputs_transpose) #[4, 4]expected
python tensorflow matrix-multiplication tensor
asked Nov 10 at 9:25
Cindy
84
add a comment |
up vote
0
down vote
favorite
I am trying to do matmul of two tensors, one is [None, 4, 256], and the other is its transpose (I use tf.transpose and got a tensor [256, 4, None]). The expected result is a [4, 4] tensor. When I use matmul, it returns an error. I am wondering, how can I get the expected result? Thank you!
#inputs: [None, 4, 256]
inputs_transpose = tf.transpose(inputs, perm = [0, 2, 1]) #[None, 256, 4]
temp_weights = tf.matmul(inputs, inputs_transpose) #[4, 4]expected
python tensorflow matrix-multiplication tensor
asked Nov 10 at 9:25
Cindy
84
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I am trying to do matmul of two tensors, one is [None, 4, 256], and the other is its transpose (I use tf.transpose and got a tensor [256, 4, None]). The expected result is a [4, 4] tensor. When I use matmul, it returns an error. I am wondering, how can I get the expected result? Thank you!
#inputs: [None, 4, 256]
inputs_transpose = tf.transpose(inputs, perm = [0, 2, 1]) #[None, 256, 4]
temp_weights = tf.matmul(inputs, inputs_transpose) #[4, 4]expected
python tensorflow matrix-multiplication tensor
asked Nov 10 at 9:25
Cindy
84
I am trying to do matmul of two tensors, one is [None, 4, 256], and the other is its transpose (I use tf.transpose and got a tensor [256, 4, None]). The expected result is a [4, 4] tensor. When I use matmul, it returns an error. I am wondering, how can I get the expected result? Thank you!
#inputs: [None, 4, 256]
inputs_transpose = tf.transpose(inputs, perm = [0, 2, 1]) #[None, 256, 4]
temp_weights = tf.matmul(inputs, inputs_transpose) #[4, 4]expected
python tensorflow matrix-multiplication tensor
python tensorflow matrix-multiplication tensor
asked Nov 10 at 9:25
Cindy
84
asked Nov 10 at 9:25
Cindy
84
edited Nov 10 at 9:45
asked Nov 10 at 9:25
Cindy
84
asked Nov 10 at 9:25
Cindy
84
asked Nov 10 at 9:25
Cindy
84
84
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
up vote
0
down vote
From Tensowflow docs
"Note: This function diverges from default Numpy behavior for float and string types when None is present in a Python list or scalar. Rather than silently converting None values, an error will be thrown."
Tensowflow does not accept None values while creating tensors.
I tried to recreate the setup you had on my system and got this error message:
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [None, 4, 256]. Consider casting elements to a supported type.
You would need to explicitly handle the None by replacing it with a 0 before attempting to use the python list.
answered Nov 10 at 10:42
Paritosh Singh
74112
add a comment |
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%2f53237598%2ftensorflow-matmul-how-to-deal-with-channel-none%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
up vote
0
down vote
From Tensowflow docs
"Note: This function diverges from default Numpy behavior for float and string types when None is present in a Python list or scalar. Rather than silently converting None values, an error will be thrown."
Tensowflow does not accept None values while creating tensors.
I tried to recreate the setup you had on my system and got this error message:
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [None, 4, 256]. Consider casting elements to a supported type.
You would need to explicitly handle the None by replacing it with a 0 before attempting to use the python list.
answered Nov 10 at 10:42
Paritosh Singh
74112
add a comment |
up vote
0
down vote
From Tensowflow docs
"Note: This function diverges from default Numpy behavior for float and string types when None is present in a Python list or scalar. Rather than silently converting None values, an error will be thrown."
Tensowflow does not accept None values while creating tensors.
I tried to recreate the setup you had on my system and got this error message:
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [None, 4, 256]. Consider casting elements to a supported type.
You would need to explicitly handle the None by replacing it with a 0 before attempting to use the python list.
answered Nov 10 at 10:42
Paritosh Singh
74112
add a comment |
up vote
0
down vote
up vote
0
down vote
From Tensowflow docs
"Note: This function diverges from default Numpy behavior for float and string types when None is present in a Python list or scalar. Rather than silently converting None values, an error will be thrown."
Tensowflow does not accept None values while creating tensors.
I tried to recreate the setup you had on my system and got this error message:
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [None, 4, 256]. Consider casting elements to a supported type.
You would need to explicitly handle the None by replacing it with a 0 before attempting to use the python list.
answered Nov 10 at 10:42
Paritosh Singh
74112
From Tensowflow docs
"Note: This function diverges from default Numpy behavior for float and string types when None is present in a Python list or scalar. Rather than silently converting None values, an error will be thrown."
Tensowflow does not accept None values while creating tensors.
I tried to recreate the setup you had on my system and got this error message:
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [None, 4, 256]. Consider casting elements to a supported type.
You would need to explicitly handle the None by replacing it with a 0 before attempting to use the python list.
answered Nov 10 at 10:42
Paritosh Singh
74112
answered Nov 10 at 10:42
Paritosh Singh
74112
answered Nov 10 at 10:42
Paritosh Singh
74112
answered Nov 10 at 10:42
Paritosh Singh
74112
74112
add a comment |
add a comment |
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.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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%2f53237598%2ftensorflow-matmul-how-to-deal-with-channel-none%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
