Is there a way to extract partial derivatives of specific layers in deep learning toolbox?
2 次查看(过去 30 天)
显示 更早的评论
Hi,
I asked this question last year, in which I would like to know if it is possible to extract partial derivatives
involved in back propagation, for the parameters
of layer
so that I can use
for other purpose. At that time, the latest MATLAB version is 2019b, and I was told in the above post that it is only possible when the final output y is a scalar, while my desired y can be a vector, matrix or even a tensor (e.g. reconstruction tasks).
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/408645/image.png)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/408650/image.png)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/408655/image.png)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/408660/image.png)
Now, is it possible to extract the partial derivatives of layer
in 2020b? Thanks.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/408665/image.png)
0 个评论
回答(1 个)
Amanpreetsingh Arora
2020-11-12
As mentioned in the answer to the question referred by you, the only way to find partial derivatives of a tensor is by looping over elements and calling "dlgradient" as "dlgradient" only supports scalar input for auto differentiation. However, I understand your concern that this will waste time recomputing overlapping traces. In order to improve time performance, you can call "dlgradient" with 'RetainData' parameter set to 'true' which will retain the intermediate computation of gradient and any subsequent calls to the function will reuse these intermediate computations. Refer to the following documentation for more information on this.
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!