Deep Learning for Computer Vision (Andrej Karpathy, OpenAI)

Keras

Keras (inferred)

“90% of the use cases are probably addressable with things like KAS. So KAS would be my go-to number one uh thing to look at.”— Andrej Karpathy

Torch

“I've used Torch for a long time. I still really like Torch. It's very lightweight, interpretable. It works just just fine.”— Andrej Karpathy

TensorFlow

Google (inferred)

“Keras is a layer over TensorFlow or Theano. Uh and basically it's just a higher level API over either of those.”— Andrej Karpathy

Theano

“Keras is a layer over TensorFlow or Theano. Uh and basically it's just a higher level API over either of those.”— Andrej Karpathy

NVIDIA DIGITS DevBox

NVIDIA

“Nvidia uh has these digits dev boxes that you can buy. They have Titan X GPUs which are strong GPUs.”— Andrej Karpathy

NVIDIA DGX-1

NVIDIA

“you can buy DGX1, which has the newest Pascal P100 GPUs. Unfortunately, the DGX1 is about $130,000. So, this is kind of an expensive supercomputer.”— Andrej Karpathy

NVIDIA Titan X

NVIDIA

“They have Titan X GPUs which are strong GPUs.”— Andrej Karpathy

NVIDIA Tesla K80

NVIDIA

“those are powerful GPUs K80s that would be available to you”— Andrej Karpathy

Microsoft Azure

Microsoft

“Microsoft Azure is coming up, Azure is coming up with its own offering soon. Uh, so I think uh they've announced it and it's in some kind of a beta stage”— Andrej Karpathy

Cirrascale

Cirrascale (inferred)

“At OpenAI for example, you use Cirrus Scale. So Serale is much more a slightly different model. You can't spin up GPUs on demand, but they allow you to rent a box in the cloud.”— Andrej Karpathy

NVIDIA CUDA

NVIDIA

“we're talking about uh Nvidia releasing the CUDA library that allows you to efficiently create all these matrix vector operations and apply them on arrays of numbers.”— Andrej Karpathy

Caffe

“neural network called Alexet running in cafe. By interacting with the network, we can see what some of the neurons are doing.”— Andrej Karpathy