How could i train my network on GPU?

Question

Hind Haboubi 2021-4-24

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/812155-how-could-i-train-my-network-on-gpu

评论： Hind Haboubi 2021-4-28

Hello guys, this is my code and i don't know how to train it on single GPU? Can you help me please. i have download GPU Coder ut i don't know what to do with it?

imageSize = [224 224 3];
load Damagevehicle
numClasses = 1;
anchorBoxes = [
    43 59
    18 22
    23 29
    84 109
];
base = resnet50;
inputlayer = base.Layers(1);
middle = base.Layers(2:174);
finallayer = base.Layers(174:end);
baseNetwork = [inputlayer
    middle
    finallayer];
featureLayer = 'activation_40_relu';
lgraph = yolov2Layers(imageSize,numClasses,anchorBoxes,base,featureLayer);
options = trainingOptions('sgdm','MiniBatchSize',128,'InitialLearnRate',1e-3,'MaxEpochs',1,'CheckpointPath',tempdir,...
    'Shuffle','every-epoch','ExecutionEnvironment','auto');
damageDataset = ddd;
[detector,info] = trainYOLOv2ObjectDetector(damageDataset,lgraph,options);

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Tarunbir Gambhir 2021-4-27

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/812155-how-could-i-train-my-network-on-gpu#answer_685685

编辑：Tarunbir Gambhir 2021-4-27

For training the network on a single particular GPU, you can select that GPU before you start the training and set the 'ExecutionEnvironment' as 'gpu' in trainingOptions(). You can refer this documentation for further information.