MATLAB Answers

0

train convolution neural network from scratch

Parul Sahi 님이 질문을 제출함. 11 Jan 2018
최근 활동 Parul Sahi 님이 편집함. 12 Jan 2018
https://in.mathworks.com/matlabcentral/fileexchange/62990-deep-learning-tutorial-series?requestedDomain=true
In the code demo_trainfromscratch in the above link:
fc1 = fullyConnectedLayer(64,'BiasLearnRateFactor',2);
how are 64 filters chosen in fc1.
Also
fc1.Weights = single(randn([64 576])*0.1);
what does 576 indicate here and how are these values obtained.

  댓글 수: 0

로그인 to comment.

답변 수: 0


Translated by