Driving into the distance — notes on ML, CUDA, Python, and beyond.https://foreveryounggithub.github.io/https://foreveryounggithub.github.io/en/posts/sketchy_rendering/https://foreveryounggithub.github.io/en/posts/sketchy_rendering/A survey of tools for creating hand-drawn/sketchy style data visualizations: rough.js, draw.io, matplotlib xkcd, chart.xkcd, and cutecharts.Tue, 19 Apr 2022 00:00:00 GMThttps://foreveryounggithub.github.io/en/posts/model_speed_vs_size/https://foreveryounggithub.github.io/en/posts/model_speed_vs_size/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.Fri, 04 Mar 2022 13:27:08 GMThttps://foreveryounggithub.github.io/en/posts/patch_based_local_descriptor/https://foreveryounggithub.github.io/en/posts/patch_based_local_descriptor/A survey of data processing and training strategies for learned image local descriptors, focusing on what distinguishes different approaches to patch-based learning.Sun, 27 Feb 2022 17:12:44 GMThttps://foreveryounggithub.github.io/en/posts/python_cpp_extension/https://foreveryounggithub.github.io/en/posts/python_cpp_extension/Using pybind11 to create Python bindings for C++/CUDA code, with zero-copy conversion between numpy/torch tensors and Eigen/cv::Mat.Sun, 20 Sep 2020 00:00:00 GMThttps://foreveryounggithub.github.io/en/posts/numba_python/https://foreveryounggithub.github.io/en/posts/numba_python/An introduction to using numba's decorators for just-in-time compilation to speed up Python functions — easy to use, flexible, and effective.Sat, 04 Jul 2020 00:00:00 GMThttps://foreveryounggithub.github.io/en/posts/trt_preproc_npp/https://foreveryounggithub.github.io/en/posts/trt_preproc_npp/How to use NVIDIA NPP library to accelerate image preprocessing (uint8→float32) for TensorRT model inference pipelines.Wed, 17 Jun 2020 00:00:00 GMThttps://foreveryounggithub.github.io/en/posts/numba_cuda/https://foreveryounggithub.github.io/en/posts/numba_cuda/A fast introduction to CUDA's multithreaded, highly concurrent programming model using Python's numba library, designed to lower the barrier for beginners.Wed, 10 Jun 2020 00:00:00 GMT