Git Product home page Git Product logo

Comments (7)

FLming avatar FLming commented on May 25, 2024

tf.ragged.map_flat_values不会填充值,只是一个映射。BLK是作为blank,其实写什么都行。

from crnn.tf2.

kingwpf avatar kingwpf commented on May 25, 2024

image
我把这个结果打出来看了一下是这样的,这里的0只是为了可视化才会填充的吗?

from crnn.tf2.

FLming avatar FLming commented on May 25, 2024

dataset类输出的y值应该是一个sparsetensor呀?你输出的时候用to_tensor了吧。这个类方法会填充值

from crnn.tf2.

kingwpf avatar kingwpf commented on May 25, 2024

dataset类输出的y值应该是一个sparsetensor呀?你输出的时候用to_tensor了吧。这个类方法会填充值

好的好的,我的确是to_tensor了,谢谢。
另外还有一个问题要麻烦你一下,我是用自己跑的数据集,然后从头训练,loss从90左右降到50的样子就会出现inf,然后一会就变成nan了,请问你这个可能是什么问题呢?

from crnn.tf2.

FLming avatar FLming commented on May 25, 2024

ctc loss好像蛮容易跑飞了的,和数据有很大的关系。如果是梯度爆炸了的话,适度使用梯度剪裁等方式处理一下?应该不会是梯度消失大概。

from crnn.tf2.

kingwpf avatar kingwpf commented on May 25, 2024

ctc loss好像蛮容易跑飞了的,和数据有很大的关系。如果是梯度爆炸了的话,适度使用梯度剪裁等方式处理一下?应该不会是梯度消失大概。

嗯嗯,谢谢你

from crnn.tf2.

kingwpf avatar kingwpf commented on May 25, 2024

ctc loss好像蛮容易跑飞了的,和数据有很大的关系。如果是梯度爆炸了的话,适度使用梯度剪裁等方式处理一下?应该不会是梯度消失大概。

我试着加大sequence length就好了,应该是我的数据里面label长度太长导致的

from crnn.tf2.

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.