2

Specifically: I would like compress a set of coordinates, which map to the locations of 1's in a binary image, and then decode back to the original set. For instance, for a 16x16 image, the input might be something like the following:

[5, 4], [12, 5], [8, 7],....

I am not looking to recognize any spatial patterns, nor is this a time series problem because the input corresponds to just one static image. The trained autoencoder should be able to handle any array of arbitrary "coordinates", under the assumption that the data is scaled between 0 to 1 so the resolution (actual range of numbers) is inconsequential. Is this doable? What would be a good way to train it?

I have come across some image-related examples like that, but I am specifically interested in a version where the input is directly a set of coordinates, instead of passing in 1s and 0s at specific indices of a matrix. Is there any additional challenge in handling, say, encoding and decoding back to a set of floating point numbers? – HighVoltage – 2020-07-12T22:55:20.973

Updated my answer! – Nicholas James Bailey – 2020-07-13T05:58:35.977