Git Product home page Git Product logo

Comments (8)

leizhu1989 avatar leizhu1989 commented on August 27, 2024

使用的是300W数据集

from pfld_68points_pytorch.

github-luffy avatar github-luffy commented on August 27, 2024

你好作者! 我训练efficientnet-b0,第三十个epoch了loss还非常大,这正常吗? Epoch:[34 ][26 /26 ] Loss: 29673.287 lr 1e-05 average_time:3.871s remain_time:13.001h Test epochs: 5 Loss 46748736.800 mean error and failure rate mean error : 1.672 failure rate: L1 0.866

初始学习率 batchsize分别设置为多少

from pfld_68points_pytorch.

leizhu1989 avatar leizhu1989 commented on August 27, 2024

学习率是0.0001,batchsize是128,都是默认值,单卡训练的

from pfld_68points_pytorch.

github-luffy avatar github-luffy commented on August 27, 2024

学习率是0.0001,batchsize是128,都是默认值,单卡训练的

从头再跑下看看,多试几次

from pfld_68points_pytorch.

leizhu1989 avatar leizhu1989 commented on August 27, 2024

我跑完了resnet的500个epoch,loss是3000多,128batchsize,test的loss依然是170万多,这是没收敛吧,为啥会这样呢,跑几次了

from pfld_68points_pytorch.

github-luffy avatar github-luffy commented on August 27, 2024

我跑完了resnet的500个epoch,loss是3000多,128batchsize,test的loss依然是170万多,这是没收敛吧,为啥会这样呢,跑几次了

训练loss和测试loss应该是不正常的 检查下标签 最好可视化看看输入的原图和标签有没有问题 把特征点输出在图片上看看。

from pfld_68points_pytorch.

leizhu1989 avatar leizhu1989 commented on August 27, 2024

我看到了代码里面有对图片进行resize,没看到对landmarks_gt做resize,不知道是不是这个原因
train_data_transforms = tv.transforms.Compose([
tv.transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.2),
tv.transforms.Resize((args.image_size, args.image_size)),
tv.transforms.ToTensor()
])

from pfld_68points_pytorch.

leizhu1989 avatar leizhu1989 commented on August 27, 2024

你好作者貌似找到原因了,我忘了crop图的那个脚本

from pfld_68points_pytorch.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.