Boost YOLO Inference Speed and reduce Memory Footprint using ONNX-Runtime | Part-2 (Continued)

Показать описание

In this stream we would continue our project to convert Ultralytics YOLO models from their standard Pytorch (.pt) format to ONNX format to improve their infrerence speed and reduce their memory footprint by running them through onnx-runtime. Our goal in this video is to work on the pre-processor and the post-processor using only onnx-runtime and numpy to achieve the same predictions from both inference engines. For this video we would continue working on OBB (Oriented Bouding Box) models. Faced some internet issues previous stream stopped abruptly continue watching from this stream.

Github Repo:
-----

Swayam Singhal

Рекомендации по теме

Комментарии

I really appreciate your efforts! Could you help me with something unrelated: I have a SafePal wallet with USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). How can I transfer them to Binance?

ReubenOdile

Boost YOLO Inference Speed and reduce Memory Footprint using ONNX-Runtime | Part-2 (Continued)

Boost YOLO Inference Speed and reduce Memory Footprint using ONNX-Runtime | Part-1

Boost YOLO Inference Speed and reduce Memory Footprint using ONNX-Runtime | Part-2

Boost YOLO Inference Speed and reduce Memory Footprint using ONNX-Runtime | Part-2 (Continued)

5x Faster YOLOv8 on CPUs

Realtime #YOLOv8 inference from an iPad 🔥

How to Improve YOLOv8 Accuracy and Speed 🚀🎯

YOLOv8 Comparison with Latest YOLO models

Fastest YOLOv5 CPU Inference with Sparsity and DeepSparse with Mark Kurtz

Optimizing Helmet Detection with Hybrid YOLO Pipelines: A Detailed Analysis

Speed up your Machine Learning Models with ONNX

Inference with SAHI (Slicing Aided Hyper Inference) using Ultralytics YOLOv8 | Episode 60

How To Export and Optimize an Ultralytics YOLOv8 Model for Inference with OpenVINO | Episode 9

YOLO-NAS: Introducing One of The Most Efficient Object Detection Algorithms

Official Yolov7 Paper Explanation and Inference - Real-Time Object Detection At Its Zenith

Speed Estimation & Vehicle Tracking | Computer Vision | Open Source

Slicing Aided Hyper Inference for Small Object Detection - SAHI

YOLO5 Object Detection Pytorch Inference with GPU Acceleration (CUDA 11 RTX 3080)

Basically, any Yolo(N+1) vs. YoloN comparison. The faster the video - the better Yolo is.

The Wrong Batch Size Will Ruin Your Model

tinyML Talks: Demoing the world’s fastest inference engine for Arm Cortex-M

YOLO-V4: Optimal Speed & Accuracy || YOLO OBJECT DETECTION SERIES

Nvidia CUDA in 100 Seconds

How To Speed Up YOLOv8 2x using TensorRT | YOLOv8 Tutorial

SAHI: Slicing Aided Hyper Inference with YOLOX