This blog shares my research and insights on Large Language Models, Computer Vision, FPGA, and GPU architecture with kernel optimization. It serves as a hub for advanced concepts, practical impleme…

Diagrams for visualizing neural network architecture

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Published in IEEE Transactions on Artificial Intelligence

Code for the paper "DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition"