Comments (11)
Teresa907
commented on May 27, 2024
你好，请问这个问题解决了吗
from face_pytorch.
QuasarLight
commented on May 27, 2024
解决了
…---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:07
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
你好，请问这个问题解决了吗
—
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 authored the thread.Message ID: ***@***.***>
from face_pytorch.
Teresa907
commented on May 27, 2024
请问是什么原因，需要修改代码吗，是否方便分享一下
from face_pytorch.
QuasarLight
commented on May 27, 2024
第156行代码有问题，correct一直是0，具体原因我忘了，代码在学校，你可以先排查一下
…---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:28
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
请问是什么原因，需要修改代码吗，是否方便分享一下
—
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 authored the thread.Message ID: ***@***.***>
from face_pytorch.
Teresa907
commented on May 27, 2024
嗯, 非常感谢您的回复，这个我也看到了，
我看网上有这麽说，原因是因为sum中的数值如果是bool类型，那么输出的就只有０和１，所以要将sum中数据类型强行转换，转换成float的类型，不知道是不是这个原因
还有他用total = label.size(0) correct/total 这个total是不是也有问题呢，感觉是个定值，有点不太理解
————————————————
版权声明：本文为CSDN博主「从天而降小可爱」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_36411839/article/details/103497868
…------------------ 原始邮件 ------------------
发件人: "wujiyang/Face_Pytorch" ***@***.***>;
发送时间: 2022年2月17日(星期四) 晚上10:35
***@***.***>;
***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
第156行代码有问题，correct一直是0，具体原因我忘了，代码在学校，你可以先排查一下
---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:28
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
请问是什么原因，需要修改代码吗，是否方便分享一下
—
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 authored the thread.Message ID: ***@***.***>
—
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 commented.Message ID: ***@***.***>
from face_pytorch.
QuasarLight
commented on May 27, 2024
num_correct_classified = float((np.array(prediction.cpu()) == np.array(labels.data.cpu())).sum())
你用一下这行代码试试
…---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:41
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
嗯, 非常感谢您的回复，这个我也看到了，
我看网上有这麽说，原因是因为sum中的数值如果是bool类型，那么输出的就只有０和１，所以要将sum中数据类型强行转换，转换成float的类型，不知道是不是这个原因
还有他用total = label.size(0)   correct/total  这个total是不是也有问题呢，感觉是个定值，有点不太理解
————————————————
版权声明：本文为CSDN博主「从天而降小可爱」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_36411839/article/details/103497868
------------------ 原始邮件 ------------------
发件人: "wujiyang/Face_Pytorch" ***@***.***>;
发送时间: 2022年2月17日(星期四) 晚上10:35
***@***.***>;
***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
第156行代码有问题，correct一直是0，具体原因我忘了，代码在学校，你可以先排查一下
---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:28
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
请问是什么原因，需要修改代码吗，是否方便分享一下
—
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 authored the thread.Message ID: ***@***.***>
—
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 commented.Message ID: ***@***.***>
—
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 authored the thread.Message ID: ***@***.***>
from face_pytorch.
Teresa907
commented on May 27, 2024
好的，我用这个替换试试，很晚了，不打扰了，晚安。
…------------------ 原始邮件 ------------------
发件人: "wujiyang/Face_Pytorch" ***@***.***>;
发送时间: 2022年2月17日(星期四) 晚上10:48
***@***.***>;
***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
num_correct_classified = float((np.array(prediction.cpu()) == np.array(labels.data.cpu())).sum())
你用一下这行代码试试
---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:41
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
嗯, 非常感谢您的回复，这个我也看到了，
我看网上有这麽说，原因是因为sum中的数值如果是bool类型，那么输出的就只有０和１，所以要将sum中数据类型强行转换，转换成float的类型，不知道是不是这个原因
还有他用total = label.size(0)   correct/total  这个total是不是也有问题呢，感觉是个定值，有点不太理解
————————————————
版权声明：本文为CSDN博主「从天而降小可爱」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_36411839/article/details/103497868
------------------ 原始邮件 ------------------
发件人: "wujiyang/Face_Pytorch" ***@***.***>;
发送时间: 2022年2月17日(星期四) 晚上10:35
***@***.***>;
***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
第156行代码有问题，correct一直是0，具体原因我忘了，代码在学校，你可以先排查一下
---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:28
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
请问是什么原因，需要修改代码吗，是否方便分享一下
—
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 authored the thread.Message ID: ***@***.***>
—
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 commented.Message ID: ***@***.***>
—
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 authored the thread.Message ID: ***@***.***>
—
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 commented.Message ID: ***@***.***>
from face_pytorch.
Teresa907
commented on May 27, 2024
你好，我想请问一下我跑这个项目没有用预训练模型，用SERes100_IR CASIA-WebFace数据集，默认参数跑出来lfw准确率还不到0.94 ，
不知道你跑的时候有没有用预训练模型，准确率能达到多少呢？
…------------------ 原始邮件 ------------------
发件人: "wujiyang/Face_Pytorch" ***@***.***>;
发送时间: 2022年2月17日(星期四) 晚上10:48
***@***.***>;
***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
num_correct_classified = float((np.array(prediction.cpu()) == np.array(labels.data.cpu())).sum())
你用一下这行代码试试
---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:41
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
嗯, 非常感谢您的回复，这个我也看到了，
我看网上有这麽说，原因是因为sum中的数值如果是bool类型，那么输出的就只有０和１，所以要将sum中数据类型强行转换，转换成float的类型，不知道是不是这个原因
还有他用total = label.size(0)   correct/total  这个total是不是也有问题呢，感觉是个定值，有点不太理解
————————————————
版权声明：本文为CSDN博主「从天而降小可爱」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_36411839/article/details/103497868
------------------ 原始邮件 ------------------
发件人: "wujiyang/Face_Pytorch" ***@***.***>;
发送时间: 2022年2月17日(星期四) 晚上10:35
***@***.***>;
***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
第156行代码有问题，correct一直是0，具体原因我忘了，代码在学校，你可以先排查一下
---原始邮件---
发件人: ***@***.***>
发送时间: 2022年2月17日(周四) 晚上10:28
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [wujiyang/Face_Pytorch] 关于train accuracy (#52)
请问是什么原因，需要修改代码吗，是否方便分享一下
—
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 authored the thread.Message ID: ***@***.***>
—
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 commented.Message ID: ***@***.***>
—
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 authored the thread.Message ID: ***@***.***>
—
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 commented.Message ID: ***@***.***>
from face_pytorch.
SanYi2019
commented on May 27, 2024
你好，train accuracy一直为0要怎么解决呢？我用num_correct_classified = float((np.array(prediction.cpu()) == np.array(labels.data.cpu())).sum())还是为0，是不是刚开始为0，训练到后面才开始提高？
from face_pytorch.
why111222
commented on May 27, 2024
@SanYi2019 我的也是这种情况，我用num_correct_classified = float((np.array(prediction.cpu()) == np.array(labels.data.cpu())).sum())还是为0，最后怎么解决的呢，能否分享一下代码呢
from face_pytorch.
why111222
commented on May 27, 2024
@Teresa907 我用num_correct_classified = float((np.array(prediction.cpu()) == np.array(labels.data.cpu())).sum())还是为0，最后怎么解决的呢，能否分享一下代码呢
from face_pytorch.
Related Issues (20)
- Hi, could you provide the cleaned 112 version MS-Celeb-1M and the list file HOT 2
- Help! HOT 2
- ResNet100-based model
- Unable to achieve the effect on your ReadME page（SE-ResNet50-IR，Webface ） HOT 3
- Visdom successfully connected to server '>' not supported between instances of 'float' and 'NoneType' Traceback (most recent call last): File "e:/AI-pro/Insightface/Face_Pytorch-master/train_my.py", line 263, in <module> train(args) File "e:/AI-pro/Insightface/Face_Pytorch-master/train_my.py", line 155, in train total_loss.backward() File "C:\Users\Administrator\Anaconda3\lib\site-packages\torch\tensor.py", line 107, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "C:\Users\Administrator\Anaconda3\lib\site-packages\torch\autograd\__init__.py", line 93, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: cuda runtime error (59) : device-side assert triggered at C:/w/1/s/windows/pytorch/aten/src\THC/generic/THCTensorMath.cu:26 HOT 2
- How to get the original AgeDB-30 and CFP-FP test dataset?
- How to use sphere face?
- CFP-FP Dataset
- Improved Residual Bottlenecks
- closed
- Can you explain What easy_margin means?
- webface_align_train.list HOT 3
- aligned evaluation dataset with google drive link
- Pretrainned model download
- How to draw roc?
- readme.md 单词怕错误矫正
- Problem with datasets
- Softmax Loss 可视化效果图如何绘制
- Who have CASIA-WebFace-112*112 dataset
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from face_pytorch.