8000 rziga · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View rziga's full-sized avatar
👽
computer visions
👽
computer visions
5 followers · 5 following

Achievements

Achievement: Pull Sharkx2Achievement: Pair Extraordinaire

Achievements

Achievement: Pull Sharkx2Achievement: Pair Extraordinaire

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. msda-triton msda-triton Public

    Multiscale deformable attention in Triton with a PyTorch interface.

    Python 3 1

  2. JavaPostevanka JavaPostevanka Public

    A native java multiplication table implementation.

    Java 1

  3. maligrad maligrad Public

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

    Python 1

  4. nerf nerf Public

    NeRF(*) that runs in a browser.

    Jupyter Notebook

  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. 

      
  6. 
  
    
    
    
      
    
        
    
            
          numpy-is-all-you-need  numpy-is-all-you-need          Public
        
    
      
    


      
    
        An encoder-decoder transformer model written in numpy.
      
    

      
    
          
  
  Jupyter Notebook


      
    
    
    
  
    

    7. 












      
  
        

          
  
    
    

        

        

  





        

      





      

  


          



    



  

    

    

    





    

    

    

  


0