ForeverYoung
RSS FeedNotes on machine learning, CUDA, Python, and beyond. Driving into the distance.
Recent Posts
-
Data Visualization with Hand-Drawn/Sketchy Style
A survey of tools for creating hand-drawn/sketchy style data visualizations: rough.js, draw.io, matplotlib xkcd, chart.xkcd, and cutecharts.
-
Model Size vs. Inference Speed in Deep Learning
An examination of how FLOPs, parameter count, memory access volume, and memory footprint affect inference speed, with practical network design recommendations for different hardware platforms.
-
Learning Strategies for Patch-Based Local Descriptors
A survey of data processing and training strategies for learned image local descriptors, focusing on what distinguishes different approaches to patch-based learning.
-
pybind11: Python Bindings for C++/CUDA Code
Using pybind11 to create Python bindings for C++/CUDA code, with zero-copy conversion between numpy/torch tensors and Eigen/cv::Mat.
-
Numba: Accelerating Python Code with Simple Decorators
An introduction to using numba's decorators for just-in-time compilation to speed up Python functions — easy to use, flexible, and effective.