![](https://img-blog.csdnimg.cn/20201014180756724.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
人工智能
文章平均质量分 89
chinazjn
公欲善其事,必先利其器
展开
-
Edge-AI Camera智能视觉系统-基于Paddle的OCR模型迁移训练(二)
有小伙伴来咨询,第一篇文章’OpenNCC智能视觉系统-基于Paddle的OCR模型迁移训练(一)‘后续有没有成功,今天有时间赶紧发出来,使用OpenNCC来构建Edge-AI OCR摄象机 第四步:开始训练在PaddleOCR目录下打开一个终端,输入命令:python tools/train.py -c configs/rec/rec_icdar15_train.yml 2>&1 | tee train_rec.log模型开始迭代。第五...原创 2021-10-08 19:01:32 · 631 阅读 · 0 评论 -
3 steps to setup a best cost performance deep learning powered raspberry pi camera with openncc
Some people use Intel ncs2 and raspberry PI camera module to build their own edge computing system, but such a combination is difficult to deploy effectively in the final product stage.1. Raspberry PI can select a few fixed camera modules. It can not eff原创 2021-10-04 09:10:39 · 151 阅读 · 0 评论 -
Edge-ai : A night vision face blurring open camera for data privacy protection
By 2025, it is expected that there will be 1 billion cameras in the public and private fields. The edge-ai cameras with deep learning and visual analysis will also develop rapidly with the maturity of artificial intelligence technology and the improvement原创 2021-09-14 10:50:43 · 204 阅读 · 0 评论 -
如何构建私有的智能视觉系统
随着人工智能应用不断被教育和普及,我们生活中越来越多的重复的范式化行为可以使用智能视觉来替代,对于很多个人开发者,如何低成本、高效率的进行原型验证就很有意义,这个低成本不仅是硬件BOM的费用,更多的是前期的学习曲线,时间成本。自己在日常系统解决方案设计中,也面临很多这样的困惑,为此花些时间做了些调研和实践。 从实用角度出发,需要从以下几个基本原则去选择和设计方案:深度学习模型的迁移学习和推理部署现在深度学习框架已经比较成熟,像tensorflow、caffe、pytorch和百度的paddl...原创 2021-03-30 12:53:33 · 244 阅读 · 0 评论