The massive amount of RAM on the NVIDIA RTX A6000 is great for generating ultra high resolution 32K images of the Mandelbrot set. In this video I show how to use TensorFlow to create both Mandelbrot images and zooms using a GPU. Unlike deep learning, which deals well with 32bit floating point, Mandelbrot zooms must make use of the high precision of 64 bit floating point numbers. 0:29 Simple Mandelbrot Zoom 1:20 Mandelbrot code introduction 2:25 Calling my Mandelbrot generator 4:26 Looking at a 32K Mandelbrot image in Photoshop 5:20 How to generate your own Mandelbrot zoom video 6:40 Mandelbrot Zoom Video in 4K 6:15 Mandelbrot Render Code Walkthrough 10:15 Using 64bit Floats for Mandelbrot rendering 10:18 What happens when you use 32bit floats to render Mandelbrot (seizure warning shaky, video) 10:53 Shaky video ends 17:09 Conclusion Notebook: I adapted some of the coloring code found here:
Hide player controls
Hide resume playing