how to use augmentedImageDatastore for validation

1 次查看（过去 30 天）
Gent Ymeri
Gent Ymeri 2019-3-26
评论： 0xJcam 2020-11-29
Is there a way to use augmentedImageDatastore (in my case augimds30) for validation?
for e.x. I split dataset in 70 by 30 percent, and I augment like this:
augimds30 = augmentedImageDatastore([50 50 3],imds30)
but then how to use this here for validation instead of imds30?
YPred = classify(net,imds30);
YValidation = imds30.Labels;
because if I put here augimds30 I get :
No appropriate method, property, or field 'Labels' for class 'augmentedImageDatastore'.
Error in cnn (line 50)
YValidation = augimds30.Labels;
  1 个评论
0xJcam
0xJcam 2020-11-29
Hello Sr.
I already had the same question and digging on internet I found following answer...
It is not posible cause the name-value pair 'ValidationData' can support only the following types as a value:
  1. Image Data Store.
  2. Data Store.
  3. Table.
  4. Cell array of X and Y, where X represents data while Y represents corresponding labels.
https://www.mathworks.com/help/deeplearning/ref/trainingoptions.html#namevaluepairarguments
Hope this can be helpful to someone.
​

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

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

标签

产品


版本

R2018b

Community Treasure Hunt

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

Start Hunting!

Translated by