GithubHelp home page GithubHelp logo

No discriminator in the state-dict. Dicriminator will be randomly initialized load optimizer_a2kp failed, train it from scratch about eat_code HOT 5 OPEN

YZX-codesky avatar YZX-codesky commented on July 28, 2024
No discriminator in the state-dict. Dicriminator will be randomly initialized load optimizer_a2kp failed, train it from scratch

from eat_code.

Comments (5)

YZX-codesky avatar YZX-codesky commented on July 28, 2024 1

我根据代码观察,发现在提取mel时进行了裁剪,是不是每一个训练的视频数据都是裁剪成了时序长度为5的mel数据和imge数据,然后放入训练,实际训练的时候只是取了时序长度为5的视频长度部分,生成的generated["prediction"]也是5张图片,而并未使用整个视频。是这样吗? 🙏

from eat_code.

yuangan avatar yuangan commented on July 28, 2024

你好,这里的设置应该是为了兼容针对第一阶段的需要继续训练的情况,不会影响第二阶段的训练。a2kp的模型在emotion adaptation阶段因为加了一些EAM层,并只优化这些层,所以优化参数已经发生了改变,并不能用第一阶段的optimizer_a2kp,在这里是正常的。

from eat_code.

YZX-codesky avatar YZX-codesky commented on July 28, 2024

你好,这里的设置应该是为了兼容针对第一阶段的需要继续训练的情况,不会影响第二阶段的训练。a2kp的模型在emotion adaptation阶段因为加了一些EAM层,并只优化这些层,所以优化参数已经发生了改变,并不能用第一阶段的optimizer_a2kp,在这里是正常的。

万分感谢你的耐心解答,关于数据中的x["mel"]和x["sync_mel"]有什么区别哇,为什么shape不一样,sync_mel是[1, 1, 80, 16],mel是[1, 5, 1, 80, 11],其中5表示的应该是同步步长吧,为什么mel里面就没有

from eat_code.

yuangan avatar yuangan commented on July 28, 2024

mel是语音的梅尔频谱,是网络的输入之一。sync_mel是用来计算sync loss的。sync_mel的形状原因可以查看wav2vec这篇论文及其代码。这个的实现可以参考这里的定义使用.

from eat_code.

yuangan avatar yuangan commented on July 28, 2024

是的,因为用了wav2vec训出来的模型,为了计算sync_loss,需要一次生成5张图片,每张图片的生成又需要临近帧的特征,所以在这里提取mel时会有两重for循环。

from eat_code.

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.