Tinn: A tiny neural network library written in C99
1–10 of 62 posts
Re: Tinn: A tiny neural network library written in C99
#2How about in 12 kilobytes of assembly? More featureful implementation here: https://github.com/dfouhey/caffe64
Re: Tinn: A tiny neural network library written in C99
#3Single core? No AVX? What's the point of writing it in C?
Re: Tinn: A tiny neural network library written in C99
#4Single core? No AVX? What's the point of writing it in C?
It's a demo, like https://github.com/rswier/c4.
Re: Tinn: A tiny neural network library written in C99
#5Re: Tinn: A tiny neural network library written in C99
#6How about in 12 kilobytes of assembly? More featureful implementation here: https://github.com/dfouhey/caffe64
This is a lot more impressive! I'm puzzled by this bit in FAQ though:
Q. It seems that it only does 1D feature vectors?
A. Convolution and other inductive biases are only necessary when you have small data.
Re: Tinn: A tiny neural network library written in C99
#7Single core? No AVX? What's the point of writing it in C?
Minimal dependencies; people are starting to get fed up with having to bootstrap and/or compile the planet just to be able to run some software. The situation has gotten completely out of hand, especially if one is not on GNU/Linux.
Re: Tinn: A tiny neural network library written in C99
#8How about in 12 kilobytes of assembly? More featureful implementation here: https://github.com/dfouhey/caffe64
“Installing a new neural network library is typically a tremendous pain because of onerous dependencies, python version hell, complicated Makefiles, and massive code bloat.”
Finally people have started speaking up and doing something about it! May we see more of such mentality in the future, and computer industry will be a better place to work!
Re: Tinn: A tiny neural network library written in C99
#9How about in 12 kilobytes of assembly? More featureful implementation here: https://github.com/dfouhey/caffe64
“Installing a new neural network library is typically a tremendous pain because of onerous dependencies, python version hell, complicated Makefiles, and massive code bloat.” Finally people have started speaking up and doing something about it! May we see more of such mentality in the future, and computer industry will be a better place to work!
Bullshit. These days installing any major NN framework is pretty much just "pip install X". Unless you want GPU support, in which case it's just slightly more complicated.
Re: Tinn: A tiny neural network library written in C99
#10How about in 12 kilobytes of assembly? More featureful implementation here: https://github.com/dfouhey/caffe64
This is a lot more impressive! I'm puzzled by this bit in FAQ though: Q. It seems that it only does 1D feature vectors? A. Convolution and other inductive biases are only necessary when you have small data.
That page is likely not completely serious. They also write that compilers are for losers.