Once you install the Tensorflow, that contains the wide variety of files and folders. Two top level folders are particularly important. The core directory and the contrib directory.
- core directory - Contain the Tensorflow's primary packages and modules
- contrib directory - Contains the secondary package that may later merge into the core Tensorflow.
When you write a Tensorflow application, it's important to know about this packages and modules.
Here, I will list some important packages of core Tensorflow..
- tensorflow - Central package of the Tensorflow framework, commonly accessed as tf.
- tf.train - Optimziers and other classes related to training
- tf.nn - Neural Network classes and related math operations
- tf.layers - Functions related to Multilayer Neural Network
- tf.contrib - Volatile or experimental code
- tf.image - Image Processing functions
- tf.estimator - High levels tools for training and evaluation
- tf.logging - Functions that write data to a log
- tf.summary - Classes needed to generate a summary data
- tf.metrics - Functions for measuring the outcome of machine learning model
Some example of contrib directory ...
- tf.contrib.keras - Makes it possible to interface Tensorflow using the Keras interface
- tf.contrib.ffmpeg - Enables audio processing through the open-source FFMPEG toolset.
- tf.contrib.bayesflow - Contains modules related to Bayesian learning
- tf.contrib.integrate - Provides the odeint function, which integrates ordinary differntial Equations.
Thank You !