MemoryAvailable[] returns the available memory reported by the operating system. Any way to mimic this with a user defined function in older versions of Mathematica?

Hi All,

I'm hoping you can help me again, this is driving me mad!

but for the life of me, I can't get it aligned in the bottom left corner of the exported image.

I guess I'm doing something stupid, but what?! Any ideas?

@Richard Try ImagePadding -> None:

i = MatrixPlot[m, MaxPlotPoints -> {360, 360}, Frame -> False,
  PlotRangePadding -> None, ImagePadding -> None]

You can omit the Alignment option, too.

@MichaelE2 thanks, unfortunately doesn't work, still centers each item

@Richard I get this:

I don't know what you mean by "each item."

ah, sorry :/ I see I missed out an important point, my "matrices" aren't square

well, some are, but not all, I'm applying this code to many many "matrices"

@Richard What happens if you use something like this:

m = RandomReal[1, {100, 200}];
i = MatrixPlot[m, MaxPlotPoints -> {360, 360}, Frame -> False,
   PlotRangePadding -> None];
Graphics[First[i], ImageSize -> {360, 360},  PlotRange -> {{0, 360}, {0, 360}}]

also, I'm clearly formatting my code wrong, not sure why

no, my solution isn't quite correct, it puts it in the bottom left, but shrinks it to one quadrant

but, @halirutan your solution works perfectly, thanks!

I couldn't seem to understand, from couple of days, my code are saying ParallelTable::nopar: No parallel kernels available; proceeding with sequential evaluation.

But never happened before couple of day, if I'm not wrong I hardly changed any settings

is there a catch somewhere?

@Shamina Have you tried restarting Mathematica?

@halirutan Many thanks!! It works now

@CarlLange How would I train a neural network to find the highlighted points in the above picture?

I've trained neural networks before. Stacked CNNs with a couple of linear layers at the end... but there is probably a more sophisticated way?

@C.E. Cool question. My first thought is to look at the construction notebook for the YOLO network on the neural net repo. I'm outdoors today but it's a cool idea

Do you have a dataset?

I wrote a segmentation network in a recent answer, you could almost definitely repurpose it

That particular net is very fast, so it would potentially work for your end goal of active video AR

(I'm thinking of segmenting the rectangle that those points are the corner of)

@CarlLange Your results in that question are very impressive, especially that you got such great results with such little training time.

The important thing, in order to be able to find the transform for AR, is to find $n$ points with great precision.

Segmentation may not be the way to do that (?)

I did try to train Yolo and it looked like that, so yeah, it seems to work pretty well. That's just with approx. 100 photos, ~1000 annotated Pokémon cards.

Maybe it can be that basis for something, although I wouldn't know how to modify it.

Re. training data for this problem, I haven't done it yet but I can get a lot by using the algorithm that I wrote about. I can take a thousand or so photos and automatically annotate them. Then, if that works, I can take more difficult photos where that algorithm doesn't work and annotate those manually.

The problem this reminds me most about is facial key point detection, and those are usually plain CNNs. Another example is NamishNet.

But I can't use those for transfer learning, I'm pretty sure, because the problems are completely different. There are plenty of networks for detecting objects that should be suitable though, but I don't know how to adapt them. (Only thing I've tried so far: Stick a couple of linear layers to the end of VGG-16.)

@CarlLange Enjoy the time outdoors, I'll tell you when I have a dataset :)

@C.E. Even a hundred training samples would be useful I think!

I didn't think of facial key point detection. I'd say you could use them for transfer learning actually. Probably better than starting from scratch.

@C.E. I would bet that you could take NetModel["Vanilla CNN for Facial Landmark Regression"], change the LinearLayer to 8 and the Reshape to 4*2, and it would start to work with some training.

only thing is it's for very small images, but it would be a proof of concept

Well, I just tried it and tbh it did not work very well, but I still have faith :)