Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错 #43

Open
frankqianghe opened this issue Nov 5, 2019 · 13 comments

Comments

@frankqianghe
Copy link

您好:
使用您的代码我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错。为了不认错把阀值调高,又会出现认不出的情况。我初步分析是两个原因,一个是实际使用中有复杂的光照,还一个是训练数据集中大部分是欧美人脸,亚洲人脸很少。用欧美人脸训练出来的模型对亚洲人脸识别不好。请问您感觉还会有什么原因造成这种情况

@foocker
Copy link

foocker commented Dec 6, 2019

so, you solved this problem?

@Ontheway361
Copy link

emm,
for data : face occlusion, side face, ...
for align : face bbox, face align ...

@wujiyang
Copy link
Owner

wujiyang commented Mar 17, 2020

lfw的结果高并说明不了什么,能在megaface上刷高分数才行,还有就是要看你使用的什么训练集

@smartparrot
Copy link

lfw的结果高并说明不了什么,能在megaface上刷高分数才行,还有就是要看你使用的什么训练集

请问adgdb-30 cfp 测试集在哪下载呀? 我用insightface代码对训练集做了对齐,然后从你提供的云盘下载了lfw cfp adgdb30测试集, 这样行吗? 我担心的是训练集对齐方式和测试集对齐方式不一致

@smartparrot
Copy link

do you did face alignment?

@ypw-lbj
Copy link

ypw-lbj commented Jun 12, 2020

请问您使用预训练模型了吗?

@wolfworld6
Copy link

您好:
使用您的代码我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错。为了不认错把阀值调高,又会出现认不出的情况。我初步分析是两个原因,一个是实际使用中有复杂的光照,还一个是训练数据集中大部分是欧美人脸,亚洲人脸很少。用欧美人脸训练出来的模型对亚洲人脸识别不好。请问您感觉还会有什么原因造成这种情况

hello,when i training,the lfw acc was as follows,how i can solve it?
image

@QuasarLight
Copy link

QuasarLight commented Dec 21, 2020 via email

@wolfworld6
Copy link

Maybe the lr you used is too big. What machine are you using?

---原始邮件--- 发件人: "wolfworld6"<[email protected]> 发送时间: 2020年12月21日(周一) 下午4:03 收件人: "wujiyang/Face_Pytorch"<[email protected]>; 抄送: "Subscribed"<[email protected]>; 主题: Re: [wujiyang/Face_Pytorch] 使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错 (#43) 您好: 使用您的代码我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错。为了不认错把阀值调高,又会出现认不出的情况。我初步分析是两个原因,一个是实际使用中有复杂的光照,还一个是训练数据集中大部分是欧美人脸,亚洲人脸很少。用欧美人脸训练出来的模型对亚洲人脸识别不好。请问您感觉还会有什么原因造成这种情况 hello,when i training,the lfw acc was as follows,how i can solve it? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

tesla v100, however i changed the lr=0.01,0.001,it is still so

@QuasarLight
Copy link

QuasarLight commented Dec 22, 2020 via email

@wolfworld6
Copy link

did you turn the option shuffle in dataloader into true? 

---原始邮件--- 发件人: "wolfworld6"<[email protected]> 发送时间: 2020年12月22日(周二) 中午11:36 收件人: "wujiyang/Face_Pytorch"<[email protected]>; 抄送: "MaoCai"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [wujiyang/Face_Pytorch] 使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错 (#43) Maybe the lr you used is too big. What machine are you using? … ---原始邮件--- 发件人: "wolfworld6"<[email protected]> 发送时间: 2020年12月21日(周一) 下午4:03 收件人: "wujiyang/Face_Pytorch"<[email protected]>; 抄送: "Subscribed"<[email protected]>; 主题: Re: [wujiyang/Face_Pytorch] 使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错 (#43) 您好: 使用您的代码我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错。为了不认错把阀值调高,又会出现认不出的情况。我初步分析是两个原因,一个是实际使用中有复杂的光照,还一个是训练数据集中大部分是欧美人脸,亚洲人脸很少。用欧美人脸训练出来的模型对亚洲人脸识别不好。请问您感觉还会有什么原因造成这种情况 hello,when i training,the lfw acc was as follows,how i can solve it? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe. tesla v100, however i changed the lr=0.01,0.001,it is still so — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

no,the shuffle value is false, trainloader = data.DataLoader(dataset, batch_size=64, shuffle=False, num_workers=2, drop_last=False),did you use lfw.py or lfw_2.py?

@QuasarLight
Copy link

QuasarLight commented Dec 22, 2020 via email

@wolfworld6
Copy link

try to turn the shuffle into true ---原始邮件--- 发件人: "wolfworld6"<[email protected]> 发送时间: 2020年12月22日(周二) 下午2:18 收件人: "wujiyang/Face_Pytorch"<[email protected]>; 抄送: "MaoCai"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [wujiyang/Face_Pytorch] 使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错 (#43) did you turn the option shuffle in dataloader into true?  … ---原始邮件--- 发件人: "wolfworld6"<[email protected]> 发送时间: 2020年12月22日(周二) 中午11:36 收件人: "wujiyang/Face_Pytorch"<[email protected]>; 抄送: "MaoCai"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [wujiyang/Face_Pytorch] 使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错 (#43) Maybe the lr you used is too big. What machine are you using? … ---原始邮件--- 发件人: "wolfworld6"<[email protected]> 发送时间: 2020年12月21日(周一) 下午4:03 收件人: "wujiyang/Face_Pytorch"<[email protected]>; 抄送: "Subscribed"<[email protected]>; 主题: Re: [wujiyang/Face_Pytorch] 使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错 (#43) 您好: 使用您的代码我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错。为了不认错把阀值调高,又会出现认不出的情况。我初步分析是两个原因,一个是实际使用中有复杂的光照,还一个是训练数据集中大部分是欧美人脸,亚洲人脸很少。用欧美人脸训练出来的模型对亚洲人脸识别不好。请问您感觉还会有什么原因造成这种情况 hello,when i training,the lfw acc was as follows,how i can solve it? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe. tesla v100, however i changed the lr=0.01,0.001,it is still so — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe. no,the shuffle value is false, trainloader = data.DataLoader(dataset, batch_size=64, shuffle=False, num_workers=2, drop_last=False),did you use lfw.py or lfw_2.py? — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

sorry,my bad,i found my pairs.txt is wrong in the gdb mode.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

8 participants