Tensorflow mapping channels while keeping other dimensionTensorflow multi-dimension argmaxTensorflow - matmul of input matrix with batch dataTypeError: Invalid dimensions for image data in tensorflowTensorflow, how to multiply a 2D tensor (matrix) by corresponding elements in a 1D vectorN-D tensor matrix multiplication with tensorflowexpanding dimensions and replicating data in tensorflowKeeping weight matrix constant in TensorFlowTensorflow Dimension UnderstandingMatrix multiplication over specific dimensions in tensorflow (or numpy)Tensorflow: zip over first dimension of two tensors of different shape
How can I practically buy stocks?
How do I check if a string is entirely made of the same substring?
How do I produce this Greek letter koppa: Ϟ in pdfLaTeX?
Find a stone which is not the lightest one
Work requires me to come in early to start computer but wont let me clock in to get paid for it
Find the identical rows in a matrix
What was Apollo 13's "Little Jolt" after MECO?
Multiple fireplaces in an apartment building?
All ASCII characters with a given bit count
Is there really no use for MD5 anymore?
Magical attacks and overcoming damage resistance
Older movie/show about humans on derelict alien warship which refuels by passing through a star
Will I lose my paid in full property
What does a straight horizontal line above a few notes, after a changed tempo mean?
Can a level 2 Warlock take one level in rogue, then continue advancing as a warlock?
Retract an already submitted recommendation letter (written for an undergrad student)
Contradiction proof for inequality of P and NP?
What to do with someone that cheated their way through university and a PhD program?
Apply a different color ramp to subset of categorized symbols in QGIS?
Co-worker works way more than he should
Why did Rep. Omar conclude her criticism of US troops with the phrase "NotTodaySatan"?
Is Diceware more secure than a long passphrase?
Can I criticise the more senior developers around me for not writing clean code?
A strange hotel
Tensorflow mapping channels while keeping other dimension
Tensorflow multi-dimension argmaxTensorflow - matmul of input matrix with batch dataTypeError: Invalid dimensions for image data in tensorflowTensorflow, how to multiply a 2D tensor (matrix) by corresponding elements in a 1D vectorN-D tensor matrix multiplication with tensorflowexpanding dimensions and replicating data in tensorflowKeeping weight matrix constant in TensorFlowTensorflow Dimension UnderstandingMatrix multiplication over specific dimensions in tensorflow (or numpy)Tensorflow: zip over first dimension of two tensors of different shape
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;
I am trying to map a set of activations X of size (?, 200, 300, 2000)
to a representation (?, 200, 300, 100).
For this I have a weight matrix W of size (2000, 100). How can I achieve that each (?, x1, y1, 2000) is multiplied correctly? I tried tf.matmul and tf.tensordot but couldnt get it to work.
tensorflow tensor
asked Mar 22 at 16:29
oeboeb
629
add a comment |
I am trying to map a set of activations X of size (?, 200, 300, 2000)
to a representation (?, 200, 300, 100).
For this I have a weight matrix W of size (2000, 100). How can I achieve that each (?, x1, y1, 2000) is multiplied correctly? I tried tf.matmul and tf.tensordot but couldnt get it to work.
tensorflow tensor
asked Mar 22 at 16:29
oeboeb
629
add a comment |
I am trying to map a set of activations X of size (?, 200, 300, 2000)
to a representation (?, 200, 300, 100).
For this I have a weight matrix W of size (2000, 100). How can I achieve that each (?, x1, y1, 2000) is multiplied correctly? I tried tf.matmul and tf.tensordot but couldnt get it to work.
tensorflow tensor
asked Mar 22 at 16:29
oeboeb
629
I am trying to map a set of activations X of size (?, 200, 300, 2000)
to a representation (?, 200, 300, 100).
For this I have a weight matrix W of size (2000, 100). How can I achieve that each (?, x1, y1, 2000) is multiplied correctly? I tried tf.matmul and tf.tensordot but couldnt get it to work.
tensorflow tensor
tensorflow tensor
asked Mar 22 at 16:29
oeboeb
629
asked Mar 22 at 16:29
oeboeb
629
asked Mar 22 at 16:29
oeboeb
629
asked Mar 22 at 16:29
oeboeb
629
asked Mar 22 at 16:29
oeboeb
629
629
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
This should help you (going with smaller shapes to speed up the computation):
X = np.ones(((5, 2, 3, 7)))
W = np.ones((X.shape[3], 10))
X_reshaped = tf.reshape(X, [-1, X.shape[3]])
# Shape: (30, 7)
y = tf.matmul(X_reshaped, W)
# Shape: (30, 10)
y_reshaped = tf.reshape(y, [-1, X.shape[1], X.shape[2], 10])
# Shape: (5, 2, 3, 10)
answered Mar 22 at 16:43
gorjangorjan
1,435617
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%2f55303989%2ftensorflow-mapping-channels-while-keeping-other-dimension%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
This should help you (going with smaller shapes to speed up the computation):
X = np.ones(((5, 2, 3, 7)))
W = np.ones((X.shape[3], 10))
X_reshaped = tf.reshape(X, [-1, X.shape[3]])
# Shape: (30, 7)
y = tf.matmul(X_reshaped, W)
# Shape: (30, 10)
y_reshaped = tf.reshape(y, [-1, X.shape[1], X.shape[2], 10])
# Shape: (5, 2, 3, 10)
answered Mar 22 at 16:43
gorjangorjan
1,435617
add a comment |
This should help you (going with smaller shapes to speed up the computation):
X = np.ones(((5, 2, 3, 7)))
W = np.ones((X.shape[3], 10))
X_reshaped = tf.reshape(X, [-1, X.shape[3]])
# Shape: (30, 7)
y = tf.matmul(X_reshaped, W)
# Shape: (30, 10)
y_reshaped = tf.reshape(y, [-1, X.shape[1], X.shape[2], 10])
# Shape: (5, 2, 3, 10)
answered Mar 22 at 16:43
gorjangorjan
1,435617
add a comment |
This should help you (going with smaller shapes to speed up the computation):
X = np.ones(((5, 2, 3, 7)))
W = np.ones((X.shape[3], 10))
X_reshaped = tf.reshape(X, [-1, X.shape[3]])
# Shape: (30, 7)
y = tf.matmul(X_reshaped, W)
# Shape: (30, 10)
y_reshaped = tf.reshape(y, [-1, X.shape[1], X.shape[2], 10])
# Shape: (5, 2, 3, 10)
answered Mar 22 at 16:43
gorjangorjan
1,435617
This should help you (going with smaller shapes to speed up the computation):
X = np.ones(((5, 2, 3, 7)))
W = np.ones((X.shape[3], 10))
X_reshaped = tf.reshape(X, [-1, X.shape[3]])
# Shape: (30, 7)
y = tf.matmul(X_reshaped, W)
# Shape: (30, 10)
y_reshaped = tf.reshape(y, [-1, X.shape[1], X.shape[2], 10])
# Shape: (5, 2, 3, 10)
answered Mar 22 at 16:43
gorjangorjan
1,435617
answered Mar 22 at 16:43
gorjangorjan
1,435617
answered Mar 22 at 16:43
gorjangorjan
1,435617
answered Mar 22 at 16:43
gorjangorjan
1,435617
1,435617
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.
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%2f55303989%2ftensorflow-mapping-channels-while-keeping-other-dimension%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
