PyTorch - Fast Differentiable Dynamic Graphs in Python

PyTorch - Fast Differentiable Dynamic Graphs in Python

Strange Loop Conference via YouTube Direct link

Intro

1 of 18

1 of 18

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

PyTorch - Fast Differentiable Dynamic Graphs in Python

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Overview of the talk
  3. 3 Machine Translation
  4. 4 Adversarial Networks
  5. 5 Adversarial Nets
  6. 6 Chained Together
  7. 7 Trained with Gradient Descent
  8. 8 Computation Graph Toolkits Declarative Toolkits
  9. 9 Imperative Toolkits
  10. 10 Seamless GPU Tensors
  11. 11 Neural Networks
  12. 12 Python is slow
  13. 13 Types of typical operators
  14. 14 Add - Mul A simple use-case
  15. 15 High-end GPUs have faster memory
  16. 16 GPUs like parallelizable problems
  17. 17 Compilation benefits
  18. 18 Tracing JIT

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.