ML Python

About

Applications

HoudiniUnreal EngineUnity 3DNukeMayaBlenderZBrushPythonMixed RealityMachine LearningGraphic DesignExtras
About

Site created with Notion, Super & Cluster

← Back

Snippets

ML Operations

morphingdesign/pythonLib

Library of Python scripts for tools and operations in various software used in my workflows. - morphingdesign/pythonLib

morphingdesign/pythonLib

Production Protocol

Conventions

2D Matrix: capitalize variable names

  • Case: features

1D Vector: lowercase variable names

  • Case: labels

TensorFlow

Sequential Model Considerations

Train / Test Sets

Decrease the test size for smaller overall data sets. (~25%) otherwise aim for ~33%.

Batch Size

If not specified, the default batch size is 32. When training model with verbose, output displays batch number rather than each training feature.

tf.keras.Sequential | TensorFlow Core v2.4.1

Sequential groups a linear stack of layers into a tf.keras.Model.

Resources

Training Outline

Example workflow using the Iris classification problem.

Custom training: walkthrough | TensorFlow Core

This guide uses machine learning to categorize Iris flowers by species. It uses TensorFlow to: Build a model, Train this model on example data, and Use the model to make predictions about unknown data. This guide uses these high-level TensorFlow concepts: This tutorial is structured like many TensorFlow programs: Import and parse the dataset.

Custom training: walkthrough | TensorFlow Core

Troubleshooting (TF1)

Uninitialized Variable

Errors with this notification could be a result of the global variable initializer not being run or being run before a variable is created.

init=tf.global_variables_initializer()

On This Page

  • Snippets
  • ML Operations
  • Production Protocol
  • Conventions
  • TensorFlow
  • Sequential Model Considerations
  • Train / Test Sets
  • Batch Size
  • Resources
  • Training Outline
  • Troubleshooting (TF1)
  • Uninitialized Variable