How to use MATLAB deep learning without GPU?

3 ビュー (過去 30 日間)

h612 2017 年 4 月 7 日

コメント済み: h612 2017 年 5 月 15 日

I'm having a problem in running nn training with

net = trainNetwork(trainingSet, layers, opts);
count = gpuDeviceCount --> 0
*bold*

I used activations earlier

trainingFeatures = activations(convnet, trainingSet, featureLayer, ...
    'MiniBatchSize', 32,'OutputAs', 'columns');

But I'm not sure How I can use them in the same way with edited layers.. Anyhelp would be highly appreciated.s

Joss Knight 2017 年 4 月 13 日

You need to actually state what the problem is, e.g. show the error message or explain what is preventing you doing what you want to do.

h612 2017 年 4 月 29 日

Solved by using Matconvnet. TQ

Tejashree Gore 2017 年 4 月 30 日

How did you use Matconvnet?

h612 2017 年 5 月 15 日

You can get it from http://www.vlfeat.org/matconvnet/ ans start with examples. Or start with 2017a version. I prefer the former.

Help Center および File Exchange で Image Data Workflows についてさらに検索

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

Translated by