Code Monkey home page Code Monkey logo

autograd-hacks's Introduction

autograd-hacks

Extract useful quantities from PyTorch autograd

Per-example gradients

autograd_hacks.add_hooks(model)
output = model(data)
loss_fn(output, targets).backward()
autograd_hacks.compute_grad1()

# param.grad: gradient averaged over the batch
# param.grad1[i]: gradient with respect to example i

for param in model.parameters():
  assert(torch.allclose(param.grad1.mean(dim=0), param.grad))

Hessians

(assuming ReLU activations, oherwise produces Gauss-Newton matrix)

autograd_hacks.backprop_hess(model(data), hess_type='CrossEntropy')
autograd_hacks.compute_hess(model)
print(param.hess)  # print Hessian of param

autograd-hacks's People

Contributors

yaroslavvb avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.