Error using trainNetwork (line 183) Invalid validation data. The output size (10) of the last layer does not match the number of classes (1).

35 次查看（过去 30 天）
Steven Chou
Steven Chou 2021-6-10
回答： Anshika Chaurasia 2021-6-16
layers = [
imageInputLayer([28 28 1]) %¹Ï¼h¿é¤Jpixel RGB or Grayscale
convolution2dLayer(3,8,'Padding','same') %²Ä¤@¼hconvolution pooling
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,16,'Padding','same') %²Ä¤G¼hconvolution pooling
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer
fullyConnectedLayer(10)
softmaxLayer
classificationLayer];

请先登录，再回答此问题。

回答（1 个）

Anshika Chaurasia
Anshika Chaurasia 2021-6-16
Hi,
This error can occur because the number of classes defined in the neural network layers is not equal to the number of classes (categories) of the validation data.
I would suggest you to match the outputSize of fullyConnectedLayer with the number of classes of the dataset.
Hope it helps!

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by