Medijski sadržaj
- Tweetovi
- Tweetovi i odgovori
- Medijski sadržaj, trenutna stranica.
-
after a few days of searching for the right abstractions, I got data parallelism working in
@hasktorchpic.twitter.com/ciVfZbsk1q
Prikaži ovu nit -
It is absolutely astonishing how quickly
@junjihashimoto3 was able to put this together:@hasktorch has fully migrated to libtorch 1.4.0! Thank you Junji!pic.twitter.com/3vAVfjr2mk
-
type - safe tensor math
#SeduceSomeoneInFourWordspic.twitter.com/nNnwKRFSTZ
-
thank you, I'll have a look. I was thinking about queries in terms of FOL terms as shown in the picturepic.twitter.com/x8jkaZwOQN
-
thanks
@Lowert, your generic-lens paper gave me the insight I needed to implement the HasToDevice class and instances for@hasktorch!
pic.twitter.com/36inXLKkq3
-
Here’s a fully functional convolutional neural network in Haskell. This API wraps libtorch, and the compiler checks your shapes, data types and physical devices, and it tells you how functions change them (see the hover box for unsqueeze).pic.twitter.com/1XRUv0ISl4
-
-
-
because they are Klingon? https://youtu.be/pHXg9oKoWak at around 1 min in
-
-
-
-
-
Had a blast today at
@kunsthallemuc with @cntewfik. It was really engaging and renewed our appreciation of Canadian paintings. Canadian artists established their own style using the whole world as their landscape. Just like Canadian culture.#kanadamucpic.twitter.com/zed4mdLZl7
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.