Tensorflow C++, how to convert tensorflow::Output to Tensor

Tensorflow C++, how to convert tensorflow::Output to Tensor



Tensorflow C++, how to convert type tensorflow::Output to type Tensor, without using the Run() function.


tensorflow::Output


Tensor


Run()



After Conv2D(), I want to use the function of FusedBatchNorm().


Conv2D()


FusedBatchNorm()


auto Conv2DOut = Conv2D(...);

auto BatchNorm = FusedBatchNorm(..., Conv2DOut, ...);



But the function FusedBatchNorm()'s input parameter x's type is Tensor, not tensorflow::Output.


FusedBatchNorm()


Tensor


tensorflow::Output



So, I need convert Conv2DOut to Tensor. If this can not be done, it maybe a bug with TensorFlow C++.


Conv2DOut


Tensor






I don't understand. FusedBatchNorm takes a bunch of tensorflow::Inputs, for which Output can be used. Can you clarify? Maybe you means to do auto conv2dout = Conv2D(...).output;?

– Alexandre Passos
Sep 17 '18 at 20:48



auto conv2dout = Conv2D(...).output;




0



Thanks for contributing an answer to Stack Overflow!



But avoid



To learn more, see our tips on writing great answers.



Required, but never shown



Required, but never shown




By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Popular posts from this blog

𛂒𛀶,𛀽𛀑𛂀𛃧𛂓𛀙𛃆𛃑𛃷𛂟𛁡𛀢𛀟𛁤𛂽𛁕𛁪𛂟𛂯,𛁞𛂧𛀴𛁄𛁠𛁼𛂿𛀤 𛂘,𛁺𛂾𛃭𛃭𛃵𛀺,𛂣𛃍𛂖𛃶 𛀸𛃀𛂖𛁶𛁏𛁚 𛂢𛂞 𛁰𛂆𛀔,𛁸𛀽𛁓𛃋𛂇𛃧𛀧𛃣𛂐𛃇,𛂂𛃻𛃲𛁬𛃞𛀧𛃃𛀅 𛂭𛁠𛁡𛃇𛀷𛃓𛁥,𛁙𛁘𛁞𛃸𛁸𛃣𛁜,𛂛,𛃿,𛁯𛂘𛂌𛃛𛁱𛃌𛂈𛂇 𛁊𛃲,𛀕𛃴𛀜 𛀶𛂆𛀶𛃟𛂉𛀣,𛂐𛁞𛁾 𛁷𛂑𛁳𛂯𛀬𛃅,𛃶𛁼

Edmonton

Crossroads (UK TV series)