41–50 of 61 posts
These things are always low resolution. At some point I'd like to see the state of the art move into more realistic (say ~500x500) dimensions.
These things are always low resolution. At some point I'd like to see the state of the art move into more realistic (say ~500x500) dimensions.
This is maybe the most important question for mankind that has ever been asked, so let me ask it: Would it also be possible to use this method to generate new images of attractive, half-naked female humans on the basis of an existing database of such images?
Please don't do this here.
But if you take a pencil and try to draw a cat yourself (assuming you are not a good artist) you have much higher chances to actually draw something "cute", than if you'd try to draw a woman. Human females look much more familiar, and there's something much trickier and more intimate to what you recognize as "cute" or "beautiful" in a human, than in a cat.
So, I'm pretty sure this NN would fail, but it's interesting what's actually required for it to not fail.
These things are always low resolution. At some point I'd like to see the state of the art move into more realistic (say ~500x500) dimensions.
There's far more work on GANs than PixelCNNs (see the https://github.com/hindupuravinash/the-gan-zoo ) but at least thus far, I haven't seen any GANs which appear visually competitive with Reed et al 2017's PixelCNN samples. Downside - code has not been released by DeepMind[], and you can't do CycleGAN or other stupid GAN tricks with PixelCNN AFAIK. CycleGAN is absolutely hilarious, if you haven't seen all the uses of it yet, much more interesting than generating cat faces.
[] I asked way back when and Reed said he'd try but nothing yet.
These things are always low resolution. At some point I'd like to see the state of the art move into more realistic (say ~500x500) dimensions.
I think it's in part due to the content loss piece being done using pre-trained imagenet models which typically resize images to 224x224...
This is maybe the most important question for mankind that has ever been asked, so let me ask it: Would it also be possible to use this method to generate new images of attractive, half-naked female humans on the basis of an existing database of such images?
Wait, it's actually generating new cat faces as in cats that don't exist? Some of those images looked like they had backgrounds in the corners was that also generated???
Earlier quoted context omitted.
The neural network is starting from noise, but that's not the only input, it was trained on [0] and I think it's arguable that the NN is "reproducing" the images from its training dataset in some sense. [0] https://web.archive.org/web/20150703060412/http://137.189.35...
I think it's a very interesting question, of how can we measure when a neural network is being creative? In fact, creativity is not obvious at all. It's sort of an ill-posed question if you think about it. How can you verify that a network is generating things that are not like what it was trained on, yet are... like what it was trained on? Are neural networks* forever relegated to the role of copying and interpolati…
However, NN tend to not be very space-efficient, and also don't usually "explain" the data (in the sense of reproducing it). So this test is hard to apply to them.
BTW: human creativity has much to do with expectation: how obvious it was to you already. So, people with different levels of exposureto some art discipline have different opinions on creativity... and as new styles become known, those opinions change.
Human beings also draw on other fields and experiences, not available in training data. Especially striking, to humans, is inspiration from common experiences that are not recognised as common, as in art that reveals ourselves to us; observational humour. For a computer to use this information, it seems it would need to have human experiences, a body, social interaction etc. Of course, this is a very parochial concept... pure creativity need not be so anthropocentric.
What are some potential applications of this outside of toy problems like cat pictures?
Or photo portraits of the "board members" for the About Us page of an autonomous corporation.