Message from @Deleted User
Discord ID: 567319683707961345
Sorry, bigot.
they did put a leaning AI on twitter, in less then 24 H she was the darling of /pol and a all out hardcore racist
the japanese version of tay lasted a lot longer - until it became suicidal
That is actually sad/funny.
It's fuddy.
<:pepeping:466401908811235329> Who was asking about GCHQ?
I love playing around with AI, though.
You can be a total noob now and use Tensorflow.
I made some image recognition. Let me find it.
Here
It's only 50 lines of code and the model I'm using is pre-trained.
I can still apply transfer-learning to it, though, to adjust it.
what do you guys think about 5G? I saw a lot of vids. predicting it will fk with our DNA and give us cancer? on the other hand some guys saying that these guys are overexaggurating n stuff n that this 4G is already simmilar to what we'll have, but i hear 5G is gonna be like 10x stronger?
It's a regular .PB model that's being loaded, with all the graph weights modifiable.
Lame
I'm not sure about 5G.
Also, the image recognition is NOT lame.
It can recognize 22,000 image classes.
Using someone else's pre made code is
can it recognize khazar milkers tho
Ah, but poo-pooing someone else's work is greaT?
5g is good but it's entirely Chinese controlled as if now
Oh my god i knew it
You are supposed to re-use models.
That's the point of having it and training it for months.
@Tero Is a trap indeed
I don't have a datacenter in my backyard.
@Deleted User talking about tensor flow not the model lolo
I can train a neural network, no problem. There is nothing difficult about it.
Ah.
So using Tensorflow is lame. XD
Gotcha.
<:GWjiangoOmegaLUL:389904150886088723>
Half of the AI projects are lame then.
And maybe they are...
But Tensforflow is still cool.
Actually, Keras is better.
Or easier at least.