Cute idea, but about half of these have given me very weird/unrealistic results. For instance this[1] one which, while amusing as hell, isn't exactly convincing. https://i.imgur.com/g5bHmH6.png
This Cat Does Not Exist
31–40 of 189 posts
Re: This Cat Does Not Exist
#32Re: This Cat Does Not Exist
#33Cute idea, but about half of these have given me very weird/unrealistic results. For instance this[1] one which, while amusing as hell, isn't exactly convincing. https://i.imgur.com/g5bHmH6.png
Re: This Cat Does Not Exist
#34Cute idea, but about half of these have given me very weird/unrealistic results. For instance this[1] one which, while amusing as hell, isn't exactly convincing. https://i.imgur.com/g5bHmH6.png
Re: This Cat Does Not Exist
#35Re: This Cat Does Not Exist
#36Cute idea, but about half of these have given me very weird/unrealistic results. For instance this[1] one which, while amusing as hell, isn't exactly convincing. https://i.imgur.com/g5bHmH6.png
Re: This Cat Does Not Exist
#37Re: This Cat Does Not Exist
#38Looks like there were some memes with watermarks in the training data https://i.imgur.com/iMOSUog.jpg
Re: This Cat Does Not Exist
#39Curious, is cat more complex object than human's face for ML to be trained and produced?
Might be that humans are not very good at recognizing differences between cats.
Common cuckoos lay their eggs in other birds' nests. The chicks don't necessarily look much like the host species to the human eye, but they can fool their hosts along the correct dimensions to get food from them. It's an interesting question to what degree ML algorithms trained on human dimensions could be foiled by an animal whose brain has been wired for different perceptions, or how feasible it is to train an ML algorithm on animal perception, or if it's possible to make an algorithm that successfully fools, say, both man and dog.
On the last point, for example: to make fake sounds that fool animals with different hearing ranges, presumably you have to be able to output sounds across the union of the ranges and train on sound data over the union of the ranges.
(Note: I'm not a biologist, if someone more informed wants to correct me on anything here you are welcome to do so.)