GPU :)
Nosso novo modelo.
  1. Use workers no DataLoaders (https://medium.com/swlh/pytorch-dataset-dataloader-b50193dc9855)
Workers
  1. Pin memory (http://deeplearnphysics.org/Blog/2018-10-02-Pinning-data-to-GPU.html)
  1. Mixed precision training
  1. Distributed Data Parallel
  1. Transferência de informações de GPU para CPU e de CPU para GPU

--

--

--

Senior Computer Vision Data Scientist at Conception Ro-Main (Quebec — CA). DSc in Computer Science. MTAC Brazil. https://github.com/adrianosantospb

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Adriano A. Santos

Adriano A. Santos

Senior Computer Vision Data Scientist at Conception Ro-Main (Quebec — CA). DSc in Computer Science. MTAC Brazil. https://github.com/adrianosantospb

More from Medium

Using pre-trained Vision Transformer model and ResNet model as features extractors for image…

Wasserstein GAN Paper Explained

Self-supervised learning in depth (part 1)

Advances in Yan LeCun’s cake génoise

Graph Neural Networks: a learning journey since 2008 — Graph Convolution Network