Skip to content
Pro
Block or report user

Report or block karpathy

Hide content and notifications from this user.

Learn more about blocking users

Contact Support about this user’s behavior.

Learn more about reporting abuse

Report abuse
Block or report user

Report or block karpathy

Hide content and notifications from this user.

Learn more about blocking users

Contact Support about this user’s behavior.

Learn more about reporting abuse

Report abuse

Pinned

  1. Normalizing flows in PyTorch. Current intended use is education not production.

    Jupyter Notebook 470 34

  2. Web interface for browsing, search and filtering recent arxiv submissions

    Python 3.7k 1.1k

  3. Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

    Lua 10.1k 2.4k

  4. Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

    JavaScript 9.9k 2k

  5. Efficient Image Captioning code in Torch, runs on GPU

    Jupyter Notebook 4.8k 1.2k

  6. 1
    """
    2
    Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
    3
    BSD License
    4
    """
    5
    import numpy as np

71 contributions in the last year

Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr Mon Wed Fri

Contribution activity

April 2020

Created a pull request in karpathy/covid-sanity that received 1 comment

add tweets to each paper, I think i like it

Requires a new twitter_daemon.py to run continuously. I can't yet decide if tweets should always show by default, or if they should be expandable, …

+199 −1 1 comment

Created an issue in karpathy/micrograd that received 3 comments

Incorrect gradient when non-leaf Values are re-used

Thank you @evcu for raising, my little 2D toy problem converged and instead of going on to proper tests and double checking through the recursion I…

3 comments
1 contribution in private repositories Apr 11

Seeing something unexpected? Take a look at the GitHub profile guide.

You can’t perform that action at this time.