train convolution neural network from scratch

1 次查看（过去 30 天）

Parul Sahi 2018-1-11

编辑： Parul Sahi 2018-1-12

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.

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

Find the treasures in MATLAB Central and discover how the community can help you!

Translated by