Transfer Learning with non-Image, Feature Vector data
4 views (last 30 days)
I am looking to use the DeepNetworkDesigner, as I have learned that it is useful for transfer learning. Unfortunately, most of the documentation concerns image-typed data. I am looking to use the DeepNetworkDesigner on data that is not an image. My data are simple feature vectors. All of the examples I have found are for image-data.
My inclination is to import the data as a datastore. I have not used datastores before, and I also do not know how to format them for the DeepNetworkDesigner.
Does anyone have experience with this and can they point me in the right direction?