新浪网

FPGA实现YOLOv5：从模型训练到硬件部署的完整实践

本文档将详细介绍如何从零开始训练YOLOv5目标检测模型，并将其部署到FPGA（现场可编程门阵列）上，以实现高效硬件加速。整个过程分为四个主要步骤：模型训练、模型优化、硬件部署和测试验证。每个步骤都包含详细解释、关键技术和代码示例，确保实践可行 ...
21ic

嵌入式AI部署：PyTorch模型量化与NXP i.MX RT系列移植全流程

[导读]在物联网设备智能化浪潮中，将深度学习模型部署到NXP i.MX RT系列等资源受限的嵌入式平台，已成为推动边缘计算发展的关键技术。本文以PyTorch模型为例，详细阐述从量化优化到移植落地的完整技术路径。 在物联网设备智能化浪潮中，将深度学习模型部署 ...
GitHub

micronet, a model compression and deploy lib.

micronet ├── __init__.py ├── base_module │ ├── __init__.py │ └── op.py ├── compression │ ├── README.md ...
GitHub

Titans: Learning to Memorize at Test Time

A complete PyTorch and MLX (Apple Silicon) implementation of the Titans architecture from Google Research. Titans introduce a Neural Long-term Memory (LMM) module that learns to memorize historical ...
51CTO

鸿蒙开发者社区

本文将深入研究修剪、量化、蒸馏等轻量化机器学习的五种核心技术，从而使你的神经网络更高效、更易于部署。 简介 无论你是在准备面试，还是在工作中构建机器学习系统，模型压缩都已成为一项必备技能。在大语言模型（LLM）时代，模型规模越来越大 ...
InfoQ

Scaling Large Language Model Serving Infrastructure at Meta

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. The speakers discuss Agent RFT, OpenAI’s ...
Semiconductor Engineering

Deploying PyTorch Models On Edge Devices

AI is being rapidly adopted in edge computing. As a result, it is increasingly important to deploy machine learning models on Arm edge devices. Arm-based processors are common in embedded systems ...