Transfer learning without imresize or imageDatastore

Question

Michael Benton 2018-8-12

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/414580-transfer-learning-without-imresize-or-imagedatastore

编辑： Michael Benton 2018-9-4

For many samples of small images, it would be nice to load the data into RAM and perform transfer learning without using images on slower memory (imageDatastore). Unfortunately, if I had 50x50x1 images and had to resize to go with alexnet, I will be forced to use (50x50x1/227x227x3) ~ 1.6% of the number of samples in order to keep everything in RAM.

Does anyone know a fix? A custom layer that resizes would work, that's a lot of work though.

using 2017b

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

Shounak Mitra 2018-8-20

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/414580-transfer-learning-without-imresize-or-imagedatastore#answer_333425

Hi Michael,

Thanks for your question.

If you need to resize, apply augmentedimagedatastore to your image datastore - it will be much faster than a custom readfcn, because it preserves prefetch under the hood. If you don’t need to resize, augment, or any other need for a custom readfcn, then vanilla imds is simplest.

Another option is to create a custom layer but you're right, it'll take some work.

HTH Shounak

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Michael Benton 2018-9-2

编辑：Michael Benton 2018-9-4

https://www.mathworks.com/help/nnet/ref/augmentedimagedatastore.html according to this, that can be done. I have updated to 2018a, and this works, thanks

请先登录，再进行评论。