leikunx / ai_projects Goto Github PK
View Code? Open in Web Editor NEWI am a full-stack engineer for AI projects, glad to share my experience. pratices make the top engineer.
License: MIT License
I am a full-stack engineer for AI projects, glad to share my experience. pratices make the top engineer.
License: MIT License
我的硬件环境(如果你觉得有必要的话),我的软件环境(操作系统型号 win7、python版本 3.6、各种库版本等)
我在复现第007_人脸识别实践_mxnet版insightFace 的第2步时遇到了问题
我遇到的问题:
# 获取人脸对应的人名
def get_personName_1(self, image_3d_array):
try:
if len(image_3d_array.shape) == 3:
image_4d_array = np.expand_dims(image_3d_array, 0)
elif len(image_3d_array.shape) == 4:
image_4d_array = image_3d_array
else:
raise ValueError('传入图像数据的维度既不是3维也不是4维')
feature_2d_array = self.face_vectorizer.get_feature_2d_array(image_4d_array)
#if not self.database_2d_array:
# return '找不到'
distance_1d_array = get_distance_1d_array(self.database_2d_array, feature_2d_array, self.distance_method)
isSame_1d_array = np.less(distance_1d_array, self.bestThreshold)
predict_personId_1d_array = self.personId_1d_array[isSame_1d_array]
if len(predict_personId_1d_array) == 0:
personName = 'Unvalid'
else:
min_distance_index = np.argmin(distance_1d_array)
similar_personId = self.personId_1d_array[min_distance_index]
predict_bincount_1d_array = np.bincount(predict_personId_1d_array)
similar_percent = predict_bincount_1d_array[similar_personId] / self.bincount_1d_array[similar_personId]
if similar_percent >= 0.97:
personName = self.personName_list[similar_personId]
else:
personName = 'None'
return personName + similar_percent
except Exception as ex:
print(ex)
return 'Unkown'
如果这个人没在人脸库里, 也会识别成人脸库里的某个人. 我把lfw的数据都加入训练了,识别的速度很快, 但是未加入人脸库的人经常会误识
你好,在学习你的项目经验时我发现可能有人涉及抄袭你的博客,内容雷同,发表时间稍微靠后,请你自己判断决定如何处理,以下为链接:
https://cloud.tencent.com/developer/user/2991686
FaceRecognizer_2.py中多进程,自动更新人脸数据库 功能是不是不能用? 运行出错BrokenPipeError: [Errno 32] Broken pipe?
Hi, @StevenLei2017
感谢分享,非常棒的工作 👍 👍 👍
在训练模型的时候,保存训练数据类别名称的文件应该是voc_classes.txt
吧,你在readme中写成了voc_names.txt
了,应该是个笔误。还有就是,需要安装matplotlib库。
模型部署这块我基本上跑完了,结果也差不多。
不过对于resources中的文件,有一些疑问。
FilaMono-Medium.otf
cifar10_ResNet56v2_model.162.h5
pixel_mean.pickle
这三个文件分别是什么呢,需要自己根据自己模型生成的吗
你好,我在复现第五章的时候出现了问题
问题是No such file or directory: '../resources/pixel_mean.pickle'
pixel_mean.pickle在您的文件里找不到,就运行不了这个文件,请问可以把那个代码发出来吗?
我的硬件环境(如果你觉得有必要的话),我的软件环境(操作系统型号 win7、python版本 3.6、各种库版本等)
我在复现第007_人脸识别实践_mxnet版insightFace 的第2步时遇到了问题
我遇到的问题:
我把lfw的数据都加入了人脸库了, 一启动2_demo.py加载会耗时3个小时,怎么保存成文件,下次直接加载这个文件就行?
感谢作者的开源!
请问作者 这个 yolov3支持 tensorflow serving部署嘛?
需要输入输出节点....
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.