Skip to content
View rziga's full-sized avatar
👽
computer visions
👽
computer visions

Block or report rziga

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. maligrad maligrad Public

    An array-based reverse-mode autograd engine built with NumPy.

    Python 1

  2. JavaPostevanka JavaPostevanka Public

    A native java multiplication table implementation.

    Java 1

  3. numpy-is-all-you-need numpy-is-all-you-need Public

    An encoder-decoder transformer model written in numpy.

    Jupyter Notebook

  4. rust-nn rust-nn Public

    Minimal sequential neural network written in Rust.

    Rust

  5. one line n-dimensional convolution i... one line n-dimensional convolution in numpy
    1
    import numpy as np
    2
    
                  
    3
    # even if it wraps, it is still one line :)
    4
    conv = lambda img, ker, stride, dilation: (img[tuple(np.expand_dims(np.indices(ker.shape) * np.expand_dims(dilation, at_end := tuple(range(-ker.ndim, 0))), tuple(range(1, ker.ndim+1))) + np.expand_dims(np.indices((img.shape - dilation * (np.array(ker.shape) - 1) - 1) // stride + 1) * np.expand_dims(stride, at_end), at_end))] * ker).sum(at_end)
    5
    
                  
  6. nerf nerf Public

    NeRF(*) that runs in a browser.

    Jupyter Notebook