w10schools
Login Register
  • Home
  • Tutorials
    • HTML, CSS
      • HTML, HTML5
      • CSS, CSS3
    • XML
    • JavaScript, AJAX
    • PHP
    • Ruby on Rails
      • Ruby
      • Rails
    • ASP.NET
      • ASP
      • C# .NET
    • Java
      • JSP
    • Databases
      • MySQL
      • MSSQL Server
      • Oracle
    • Web Server
      • Windows
      • Linux
      • Apache
      • IIS
    • Design
      • Dreamweaver
      • Flash
      • Photoshop
      • Fireworks
      • CorelDRAW
      • Illustrator
  • References
    • HTML
      • Bootstrap
    • CSS
      • CSS Selectors
      • Sass
    • JavaScript
    • Mobile Apps
      • Cordova
    • Ruby on Rails
      • Ruby
      • Rails
    • PHP
      • Function
      • Language
      • CodeIgniter
      • Phalcon
      • PHPUnit
      • Symfony
      • Drupal
      • Yii
      • Laravel
    • Perl
      • Perl
    • Python
      • Python
      • Django
      • NumPy
      • Pandas
      • scikit-image
      • scikit-learn
      • Statsmodels
      • Matplotlib
    • Lua
      • Lua
    • C, C++
      • C
      • C++
    • Server
      • Docker
      • Apache HTTP Server
      • Nginx
    • Database
      • PostgreSQL
    • Big Data
      • TensorFlow
    • Game Development
      • Phaser
      • LÖVE
  • Articles
    • News
    • General
      • Website Promotion
      • Online Advertising
      • Make Money Online
    • Editorials
    • Interviews
    • Web Roundups
  • Resources
    • Design
      • Fonts
      • Graphics
      • Vectors
      • Templates
      • UI (User Interface)
      • Brushes
      • Patterns, Backgrounds
      • Textures
    • Web Development
      • HTML, CSS
      • XML
      • JavaScript, AJAX
      • Ruby on Rails
      • PHP
      • Java
      • .NET
      • Python
      • Perl
      • Flash
    • Mobile Application Development
      • Mobile Development Tools
      • Swift
    • Online Services
      • Online Storage
      • Web Hosting
  • Tools
    • Generators
Edit
In Place Editing Advanced Editing
  • References
  • Big Data
  • TensorFlow
  • TensorFlow Python
  • Monitors

tf.contrib.learn.monitors.NanLoss.__init__()

tf.contrib.learn.monitors.NanLoss.__init__(loss_tensor, every_n_steps=100, fail_on_nan_loss=True)

Initializes NanLoss monitor.

Args:
  • loss_tensor: Tensor, the loss tensor.
  • every_n_steps: int, run check every this many steps.
  • fail_on_nan_loss: bool, whether to raise exception when loss is NaN.
Links:
  • https://www.tensorflow.org/versions/master/api_docs/python/contrib.learn.monitors.html#NanLoss.__init__
doc_TensorFlow
doc_TensorFlow
2025-01-10 15:47:30
Comments
Leave a Comment

Please login to continue.

Popular Articles
tf.contrib.learn.monitors.NanLoss class tf.contrib.learn.monitors.NanLoss NaN Loss monitor. Monitors loss and stops training if loss is NaN. Can either fail with exception or just st
tf.contrib.learn.monitors.NanLoss.begin() tf.contrib.learn.monitors.NanLoss.begin(max_steps=None) Called at the beginning of training. When called, the default graph is the one we are execut
tf.contrib.learn.monitors.NanLoss.end() tf.contrib.learn.monitors.NanLoss.end(session=None)
tf.contrib.learn.monitors.NanLoss.epoch_begin() tf.contrib.learn.monitors.NanLoss.epoch_begin(epoch) Begin epoch. Args: epoch: int, the epoch number. Raises: ValueError: if we've already begun
tf.contrib.learn.monitors.NanLoss.post_step() tf.contrib.learn.monitors.NanLoss.post_step(step, session)


Return to View
  • Facebook
  • Tweet
  • Digg it
  • Stumbleupon
  • Delicious
  • Plus Share

Designed by : w10schools

service@w10schools.com

Our Partners: aeeble – Providing content publishing and search solutions