The nigger brain cannot understand what a random number is.
Autoencoding Blade Runner: reconstructing films with artificial neural networks
21–30 of 39 posts
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#22Very interesting. This makes me wonder if a similar technique can be used for compression?
This is too powerful to use for product work, I think.
Professionals like to use something they can understand, and when making a BD or streaming source they know what a compression artifact looks like and which frames' bitrates to tweak to hide it. They pretty much sit there all day and just do that.
Maybe live streaming?
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#23> The model also struggles to make a recognisable reconstruction when the scene is very low contrast, especially with faces. It could be getting this wrong if his error function is calculating linear data from the given image pixels, which are in the totally not linear sRGB colorspace. That would make it badly underestimate any error in a dark image. Quick check of the PIL docs doesn't mention gamma compensation, so…
Actually, it would be even worse if it was run on gamma-corrected (proportional to light intensity) pixels. The sRGB space is designed to approximate human perception, which is only advantageous for this application.
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#24Correct me if I am wrong, but it is not so much "reconstruction" as "compression". (Or I got it wrong. Or the description is utterly unclear: reconstruct what from what.)
If it is the compression case, I am curious for the size of the compressed movie.
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#25I'm a little confused by the article: it appears to me that the input to the neural net is a series of frames, and the output is a series of frames? So it works as a filter? Or is the input key-frames, and so the net extrapolates intermediary frames from keyframes?
[ed: does indeed appear from the github page, that the input is a series of png frames, and the output is the same number of png frames, filtered through the neural net. No compression, but rather a filter operation?]
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#26The article lacks some details (I guess many can be found in cited papers), but it definitely seems to be a giant step toward usable large scale image analysis (providing a meaningful description). Maybe this could benefit google's new cpu...
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#27I'm a little confused by the article: it appears to me that the input to the neural net is a series of frames, and the output is a series of frames? So it works as a filter? Or is the input key-frames, and so the net extrapolates intermediary frames from keyframes? [ed: does indeed appear from the github page, that the input is a series of png frames, and the output is the same number of png frames, filtered through…
When one talks about autoencoding it usually means "compression"
I think it's doing something like this (but more complex) https://cs.stanford.edu/people/karpathy/convnetjs/demo/autoe... where you have a bottleneck on the network
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#28The autoencoder converts an image to a reduced code then back to the original image. The idea is similar to lossy compression, but it's geared specifically for the dataset that it's trained on.
According to the defaults in the code, it uses float32 arrays of the following sizes:
image: 144 x 256 x 3 = 110,592
code: 200
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#29The autoencoder converts an image to a reduced code then back to the original image. The idea is similar to lossy compression, but it's geared specifically for the dataset that it's trained on. According to the defaults in the code, it uses float32 arrays of the following sizes: image: 144 x 256 x 3 = 110,592 code: 200 Note that the sequence of codes that the movie is converted to could possibly be further compressed…
This should be mentioned in the article, I was looking for a simple mathematical comparison.
Re: Autoencoding Blade Runner: reconstructing films with artificial neural networks
#30What are the potential applications for an autoencoder, aside from an exercise in neural networks?
Lossy compression with super high compression rates?