Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @NimTorch
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @NimTorch
-
NimTorch proslijedio/la je Tweet
Sounds like you guys need stuff like
@NimTorch ! If I only had some support to keep developing it! But everyone seems stuck to bad tools and bad pipelines toasting their productivity...https://twitter.com/elonmusk/status/1224182478501482497 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
Since the 1 Neuron XOR became a topic… 1 hidden neuron XOR Network evolved using simulated annealing (In less then a second.. could be better) Basically a "sin" activation seems to be the keypic.twitter.com/n8oNwopZkh
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
I didn't expect it but actually this is a good read for anyone curious on where "AI" is and it's limits.https://www.wired.com/story/facebooks-ai-says-field-hit-wall …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
Impressive work. Very efficient way of doing style transfer. Style Transfer with GANs on HD Images - Towards Data Sciencehttps://towardsdatascience.com/style-transfer-with-gans-on-hd-images-88e8efcf3716 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
Finally people is starting to talk about spiking neural networks! Thanks
@elonmusk and@neuralinkHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
@v_language marketing before benchmarks, also highly suspicious...https://twitter.com/fuyutarow/status/1144032688333963265 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
We are working on a product very much inspired by this and neuroevolution in general. MNIST was a huge challenge for me in terms of CPU optimizations. Given you work at google and google cloud is probably cheap for you :) I wonder, how many VMs you had to throw at it?https://twitter.com/hardmaru/status/1138600152048910336 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
With newruntime and destructors there is a lot of potential!https://twitter.com/nim_lang/status/1136652293510717440 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
With nimline by
@fragcolor,@nim_lang and@qtproject work wonderfully together. I uploaded a quick samplehttps://github.com/sinkingsugar/nimqt-example …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is the magic behind NimTorch and the secret ingredient for seamless native performance.https://twitter.com/fragcolor/status/1087913627254906880 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We are thinking to release C automated bindings to
@PyTorch via@NimTorch. The magic lies behind@nim_lang ability to generate C headers out of generated code. Potentially any language (e.g.@JuliaLanguage) can consume them and harness the power of low-level@PyTorch.pic.twitter.com/mU6v4JPtcC
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
I know I may sound like a preacher but I'm a productivity advocate and so, actually you could also use nimpy https://github.com/yglukhov/nimpy And write a cuda kernel straight in
@nim_lang and@NimTorchpic.twitter.com/SODBW11Cvh
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
As usual training remains something only super entities can do. While this is not necessarily the case! This is exactly my inspiration and motivation to push
@NimTorch Because being able to train a partially trained network on a small device definitely should be possible.https://twitter.com/TensorFlow/status/1084878016625414154 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
NimTorch proslijedio/la je Tweet
A small teaser of the first
@unity3d plug-in we are going to release soon! Powered by@NimTorch and ATen/C10 (@PyTorch)pic.twitter.com/pvHvZfdzDY
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je Tweet
I'm surprised nobody in the
@nim_lang community noticed we have a multiplatform (arm, x86, any) SIMD vectors library (using and tested gcc, clang, vcc amazing vectorization). https://github.com/fragcolor-xyz/fragments/blob/master/fragments/math/vectors.nim … Doubt any other language could come up with such easy to use wide vectors.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
We added two new types of builds for aten and nimtorch on
#conda. lite: very small runtime (low perf tho, as it's not including any MKL/Cuda etc), statically linked (produce a single binary no deps!) static: similar to lite but includes Intl MKL (windows and linux only)Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
NimTorch proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
NimTorch proslijedio/la je Tweet
Follow up: It looks like
@PyTorch is including and linking mkl-dnn which we exclude on purpose in@NimTorch mkl-dnn library fails miserably to load and work when used in a#linux kvm virtual machine, this means at the moment PyTorch cannot run on a VM properly. (i7-7700K here)https://twitter.com/voidtarget/status/1079402807109644292 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
7,600+
Ruby/Crstalにも届きそう.
Inspired by precocial species in biology, we set out to search for neural net architectures that can already (sort of) perform various tasks even when they use random weight values.
Article: