TensorFlow Python reference documentation
haosdent TensorFlow Python reference documentation
Building Graphs
Classes and functions for building TensorFlow graphs.
Asserts and boolean checks
assertion
Constants, Sequences, and Random Values
Constant: 生成Constant Value Tensors的API
Sequences: 生成sequence的API
Random Tensors: 生成random tensors with different distributions的API
Variables
Tensor Transformations
对Tensor进行操作
Math
basic arithmetic operators
Strings
Histograms
直方图
Control Flow
TensorFlow provides several operations and classes that you can use to control the execution of operations and add conditional dependencies to your graph.
Higher Order Functions
TensorFlow provides several higher order operators to simplify the common map-reduce programming patterns
TensorArray Operations
class tf.TensorArray
Tensor Handle Operations
TensorFlow provides several operators that allows the user to keep tensors "in-place" across run calls(允许用户在运行调用时将张量保持在“原位”)
Images
图像进行操作的API
Sparse Tensors
Inputs and Readers
Data IO (Python functions)
feed data的API
Neural Network
tf.nn
- Activation Functions
- Convolution
- Pooling
- Morphological filtering
- Normalization
- Losses
- Classification
- Embeddings
- Recurrent Neural Networks
- Connectionist Temporal Classification (CTC)
- Evaluation
- Candidate Sampling
- Other Functions and Classes
Neural Network RNN Cells
Running Graphs
This library contains classes for launching graphs and executing operations.
The basic usage guide has examples of how a graph is launched in a tf.Session
.
Training
This library provides a set of classes and functions that helps train models.
Wraps python functions
TensorFlow provides allows you to wrap python/numpy functions as TensorFlow operators.
Summary Operations
This module contains ops for generating summaries.
Testing
TensorFlow provides a convenience class inheriting from unittest.TestCase
which adds methods relevant to TensorFlow tests.
BayesFlow Entropy (contrib)
BayesFlow Stochastic Tensors (contrib)
BayesFlow Variational Inference (contrib)
Variational(变分法) inference.
CRF (contrib)
Linear-chain CRF layer.
Statistical distributions (contrib)
Classes representing statistical distributions and ops for working with them.
FFmpeg (contrib)
Encoding and decoding audio using FFmpeg
Framework (contrib)
Graph Editor (contrib)
The TensorFlow Graph Editor library allows for modification of an existing tf.Graph
instance in-place.
Layers (contrib)
Ops for building neural network layers, regularizers, summaries, etc.
Learn (contrib)
High level API for learning with TensorFlow.
Monitors (contrib)
Monitors allow user instrumentation of the training process.
Losses (contrib)
Ops for building neural network losses.
RNN (contrib)
Additional RNN operations and cells.
Metrics (contrib)
Ops for evaluation metrics and summary statistics