这个 net = jit.load(r'.\weights\openpose.jit') 在哪找得到

likecu commented 2 years ago

❔Question

Additional context

github-actions[bot] commented 2 years ago

👋 Hello @likecu, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Google Colab Notebook with free GPU:
Kaggle Notebook with free GPU: https://www.kaggle.com/ultralytics/yolov5
Google Cloud Deep Learning VM. See GCP Quickstart Guide
Docker Image https://hub.docker.com/r/ultralytics/yolov5. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

zhuoxiangpang commented 2 years ago

在这个网盘里面链接：https://pan.baidu.com/s/1n8aMBfWfogBgZN8qCmHcoQ  提取码：yge5 --来自百度网盘超级会员V4的分享

------------------ 原始邮件 ------------------ 发件人: "zhuoxiangpang/ism_person_openpose" @.>; 发送时间: 2022年1月28日(星期五) 下午3:57 @.>; @.***>; 主题: [zhuoxiangpang/ism_person_openpose] 这个 net = jit.load(r'.\weights\openpose.jit') 在哪找得到 (Issue #5)

❔Question

Additional context

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you are subscribed to this thread.Message ID: @.***>

LiLangyu commented 2 years ago

你好，网盘分享过期了，可以再分享一下吗，感谢

zhuoxiangpang commented 2 years ago

链接：https://pan.baidu.com/s/1oL5wmEdZW_3KehArrK9PNw  提取码：3su3 --来自百度网盘超级会员V4的分享

------------------ 原始邮件 ------------------ 发件人: "zhuoxiangpang/ism_person_openpose" @.>; 发送时间: 2022年3月22日(星期二) 下午3:04 @.>; @.**@.>; 主题: Re: [zhuoxiangpang/ism_person_openpose] 这个 net = jit.load(r'.\weights\openpose.jit') 在哪找得到 (Issue #5)

你好，网盘分享过期了，可以再分享一下吗，感谢

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

LiLangyu commented 2 years ago

你好，加个微信好吗，我刚入门做这个，有些地方想请教一下，我可以在通过好友后提供自我介绍

zhuoxiangpang commented 2 years ago

15935130570 加这个微信吧，我也是小菜狗，不过可以相互讨论学习一下~

------------------ 原始邮件 ------------------ 发件人: "zhuoxiangpang/ism_person_openpose" @.>; 发送时间: 2022年3月23日(星期三) 中午11:40 @.>; @.**@.>; 主题: Re: [zhuoxiangpang/ism_person_openpose] 这个 net = jit.load(r'.\weights\openpose.jit') 在哪找得到 (Issue #5)

你好，加个微信好吗，我刚入门做这个，有些地方想请教一下，我可以在通过好友后提供自我介绍

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

jayendsff commented 2 years ago

您好，我也是刚开始想做一个摔倒的检测，因为刚刚入门很多逻辑都不太懂，想请教您，多有打扰了！就是我能用Openpose和yolov5单独做出来，但是想在Yolov5检测出目标框的基础上再用openpose做一个针对目标框内的人体的检测....两个算法的融合不太懂要怎么做^^.......很冒昧给您发消息,抱歉!

zhuoxiangpang commented 2 years ago

这个小demo就是这么实现的，可以先试着跑通它，一步步调 1.先通过v5识别人体后，按照v5识别人体框的坐标对图片进行裁剪（可能检测出多个人，所以这里会成为个List） 2.把裁剪出的图片传给openpose做姿态的检测即可 3.把openpose检测后的结果回拼到原来的图片中这个demo的代码写的很烂

------------------ 原始邮件 ------------------ 发件人: "zhuoxiangpang/ism_person_openpose" @.>; 发送时间: 2022年3月29日(星期二) 中午11:06 @.>; @.**@.>; 主题: Re: [zhuoxiangpang/ism_person_openpose] 这个 net = jit.load(r'.\weights\openpose.jit') 在哪找得到 (Issue #5)

您好，我也是刚开始想做一个摔倒的检测，因为刚刚入门很多逻辑都不太懂，想请教您，多有打扰了！就是我能用Openpose和yolov5单独做出来，但是想在Yolov5检测出目标框的基础上再用openpose做一个针对目标框内的人体的检测....两个算法的融合不太懂要怎么做^^.......很冒昧给您发消息,抱歉!

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

nobody-cheng commented 2 years ago

for box in boxList:
c1, c2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
x = c2[0] - c1[0]
y = c2[1] - c1[1]
if x / y >= 0.8:  # 比例>0.8 可能会是摔倒
这是对应行人相对屏幕横着摔倒但实际情况行人大概率相对屏幕是竖着摔倒

zhuoxiangpang commented 2 years ago

是的是的，在我当时的那个场景下，可以简单的通过框的宽高比做一层筛选，这部分需要根据自己的场景做修改或删除

------------------ 原始邮件 ------------------ 发件人: "zhuoxiangpang/ism_person_openpose" @.>; 发送时间: 2022年4月7日(星期四) 下午2:52 @.>; @.**@.>; 主题: Re: [zhuoxiangpang/ism_person_openpose] 这个 net = jit.load(r'.\weights\openpose.jit') 在哪找得到 (Issue #5)

           for box in boxList:                 c1, c2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))                 x = c2[0] - c1[0]                 y = c2[1] - c1[1]                 if x / y &gt;= 0.8:  # 比例&gt;0.8 可能会是摔倒

这是对应行人相对屏幕横着摔倒但实际情况行人大概率相对屏幕是竖着摔倒

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

shenshi19 commented 2 years ago

你好，加个微信好吗，我刚入门做这个，有些地方想请教一下，我可以在通过好友后提供自我介绍

你好，加个微信好吗，我刚入门做这个，有些地方想请教一下，我可以在通过好友后提供自我介绍

您好，我也是想做这个课题，我的微信是a285337147，可以方便交流一下吗

kivenyangming commented 1 year ago

思路：

对目标的宽高进行计算，如[nobody-cheng]所言；
提取目标的头和脚，当头的中心点坐标与脚的中心点坐标较为接近时判定为摔倒。（这里面的脚可以拓展为躯干）

zhuoxiangpang / ism_person_openpose