Coder Social home page Coder Social logo

greydanus / mnist1d Goto Github PK

View Code? Open in Web Editor NEW
152.0 5.0 28.0 14.45 MB

A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.

License: Apache License 2.0

Python 0.48% Jupyter Notebook 99.52%
neural-networks machine-learning convnet pytorch dataset research

mnist1d's Issues

Publication

Congrats on this dataset being prominently used in the Prince's ML textbook: https://udlbook.github.io/udlbook/ !

It made me wonder: was your paper published anywhere? It seems like it wasn't; but have you tried to publish it? I think it's really cool, so I am wondering if it kept getting rejected or if you haven't really tried to publish it.

Can not load default dataset

The default dataset seems to be broken. Not a big deal since it just automatically rebuilds it, but I though I should bring it to your attention.

from mnist1d.data import get_dataset_args, get_dataset
args = get_dataset_args()
data = get_dataset(args,  path='./mnist1d_data.pkl', download=True)
-> 
Downloading MNIST1D dataset from https://github.com/greydanus/mnist1d/raw/master/mnist1d_data.pkl   
Saving to ./mnist1d_data.pkl
Did or could not load data from ./mnist1d_data.pkl. Rebuilding dataset...

minimal repo: https://colab.research.google.com/drive/16RBVCMLXegLZ6xidI3ZBe_visT_gR5EA?usp=sharing

Packaging this dataset

Hi, thanks for contributing this dataset as open source. Motivated by "Understanding Deep Learning", I'd love to start playing with it.

I saw that the repo is not ready for packaging. As the code is rather straight forward, I was wondering if any PRs would be appreciated to package this as a python module.

This would also make it more easier to use more broadly than by using the requests package. People could just go: pip install mnist1d and have the code for augmenting and changing under their fingers. Just a thought!

Right now, I get the following:

python -m pip install git+https://github.com/greydanus/mnist1d.git@master
Collecting git+https://github.com/greydanus/mnist1d.git@master
  Cloning https://github.com/greydanus/mnist1d.git (to revision master) to /tmp/pip-req-build-eg1a_6cu
  Running command git clone --filter=blob:none --quiet https://github.com/greydanus/mnist1d.git /tmp/pip-req-build-eg1a_6cu
  Resolved https://github.com/greydanus/mnist1d.git to commit 39dd6c03785eefe60f349af94e61f864fc449644
ERROR: git+https://github.com/greydanus/mnist1d.git@master does not appear to be a Python project: neither 'setup.py' nor 'pyproject.toml' found.

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.