Git Product home page Git Product logo

conv_nn's Introduction

HW2

To change default implementation (TORCH / VECTORIZED / SCALAR) please change Enum var DEFAULT_IMPL at file

Task 1.

For batch size = 1 And 1 epoch, checked that diff_mse is the same

Mse diff:
Conv layer: 7.853249876842248e-15,
 	Pool layer: 9.127989569713765e-15,
 	Reshape layer: 9.127989569713765e-15,
 	FC layer: 2.2586452022924086e-13

Please, dont use scalar implementation for learning, it causes errors, because of

torch.no_grad()

And used only for calculation mse error.

Task 2.

  1. Implemented convolutional layer with im2col trick
  2. Pooling layer through im2col
  3. FC implemented

Task 3.

20 epochs

  1. Vectorized -
    Test set: Average loss: -0.9853, Accuracy: 9877/10000 (98.77%)
    Time:
  2. Torch -
    Test set: Average loss: -0.9853, Accuracy: 9876/10000 (98.76%) Time:

conv_nn's People

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.