MATLAB Answers

Translated by

이 페이지의 내용은 영어에서 자동 번역되었습니다. 자동 번역 기능을 해제하려면 "<a class="turn_off_mt" href="#" onclick="window._kiq.push(['set', { 'event': 'Turn off MT' }]);">여기</a>"를 클릭하십시오.

0

train convolution neural network from scratch

Asked by Parul Sahi on 11 Jan 2018
Latest activity Edited by Parul Sahi on 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.

  0 Comments

Sign in to comment.

0 Answers


Translated by