Metadata-Version: 2.1
Name: tensorflow-model-analysis
Version: 0.21.4
Summary: A library for analyzing TensorFlow models
Home-page: https://www.tensorflow.org/tfx/model_analysis
Author: Google LLC
Author-email: tensorflow-extended-dev@googlegroups.com
License: Apache 2.0
Download-URL: https://github.com/tensorflow/model-analysis/tags
Keywords: tensorflow model analysis tfx
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,<4
Description-Content-Type: text/markdown
Requires-Dist: absl-py (<0.9,>=0.7)
Requires-Dist: apache-beam[gcp] (<2.18,>=2.17)
Requires-Dist: ipywidgets (<8,>=7)
Requires-Dist: jupyter (<2,>=1)
Requires-Dist: numpy (<2,>=1.16)
Requires-Dist: pandas (<2,>=0.24)
Requires-Dist: protobuf (<4,>=3.7)
Requires-Dist: pyarrow (<1,>=0.15)
Requires-Dist: six (<2,>=1.12)
Requires-Dist: tensorflow (!=2.0.*,<3,>=1.15)
Requires-Dist: tensorflow-metadata (<0.22,>=0.21)
Requires-Dist: tfx-bsl (<0.23,>=0.21.3)
Requires-Dist: scipy (==1.2.2) ; python_version < "3"
Requires-Dist: scipy (==1.4.1) ; python_version >= "3"
Requires-Dist: avro-python3 (!=1.9.2.*,!=<2.0.0,>=1.8.1) ; python_version >= "3.0"

<!-- See: www.tensorflow.org/tfx/model_analysis/ -->

# TensorFlow Model Analysis

[![Python](https://img.shields.io/pypi/pyversions/tensorflow-model-analysis.svg?style=plastic)](https://github.com/tensorflow/model-analysis)
[![PyPI](https://badge.fury.io/py/tensorflow-model-analysis.svg)](https://badge.fury.io/py/tensorflow-model-analysis)
[![Documentation](https://img.shields.io/badge/api-reference-blue.svg)](https://www.tensorflow.org/tfx/model_analysis/api_docs/python/tfma)

*TensorFlow Model Analysis* (TFMA) is a library for evaluating TensorFlow models.
It allows users to evaluate their models on large amounts of data in a
distributed manner, using the same metrics defined in their trainer. These
metrics can be computed over different slices of data and visualized in Jupyter
notebooks.

![TFMA Slicing Metrics Browser](https://raw.githubusercontent.com/tensorflow/model-analysis/master/g3doc/images/tfma-slicing-metrics-browser.gif)

Caution: TFMA may introduce backwards incompatible changes before version 1.0.

## Installation

The recommended way to install TFMA is using the
[PyPI package](https://pypi.org/project/tensorflow-model-analysis/):

<pre class="devsite-terminal devsite-click-to-copy">
pip install tensorflow-model-analysis
</pre>

pip install from the HEAD of the git:

<pre class="devsite-terminal devsite-click-to-copy">
pip install git+https://github.com/tensorflow/model-analysis.git#egg=tensorflow_model_analysis
</pre>

pip install from a released version directly from git:

<pre class="devsite-terminal devsite-click-to-copy">
pip install git+https://github.com/tensorflow/model-analysis.git@v0.21.3#egg=tensorflow_model_analysis
</pre>

If you have cloned the repository locally, and want to test your local change,
pip install from a local folder:

<pre class="devsite-terminal devsite-click-to-copy">
pip install -e $FOLDER_OF_THE_LOCAL_LOCATION
</pre>

Currently, TFMA requires that TensorFlow is installed but does not have an
explicit dependency on the TensorFlow PyPI package. See the
[TensorFlow install guides](https://www.tensorflow.org/install/) for instructions.

To enable TFMA visualization in Jupyter Notebook:

<pre class="prettyprint">
  <code class="devsite-terminal">jupyter nbextension enable --py widgetsnbextension</code>
  <code class="devsite-terminal">jupyter nbextension install --py --symlink tensorflow_model_analysis</code>
  <code class="devsite-terminal">jupyter nbextension enable --py tensorflow_model_analysis</code>
</pre>

Note: If Jupyter notebook is already installed in your home directory, add
`--user` to these commands. If Jupyter is installed as root, or using a virtual
environment, the parameter `--sys-prefix` might be required.

### Dependencies

[Apache Beam](https://beam.apache.org/) is required to run distributed analysis.
By default, Apache Beam runs in local mode but can also run in distributed mode
using [Google Cloud Dataflow](https://cloud.google.com/dataflow/). TFMA is
designed to be extensible for other Apache Beam runners.

## Getting Started

For instructions on using TFMA, see the [get started
guide](https://github.com/tensorflow/model-analysis/blob/master/g3doc/get_started.md).

## Compatible Versions

The following table is the TFMA package versions that are compatible with each
other. This is determined by our testing framework, but other *untested*
combinations may also work.

|tensorflow-model-analysis                                                           |tensorflow    |apache-beam[gcp]|
|------------------------------------------------------------------------------------|--------------|----------------|
|[GitHub master](https://github.com/tensorflow/model-analysis/blob/master/RELEASE.md)|nightly (1.x/2.x) |2.19.0      |
|[0.21.4](https://github.com/tensorflow/model-analysis/blob/v0.21.4/RELEASE.md)      |1.15 / 2.1    |2.19.0          |
|[0.21.3](https://github.com/tensorflow/model-analysis/blob/v0.21.3/RELEASE.md)      |1.15 / 2.1    |2.17.0          |
|[0.21.2](https://github.com/tensorflow/model-analysis/blob/v0.21.2/RELEASE.md)      |1.15 / 2.1    |2.17.0          |
|[0.21.1](https://github.com/tensorflow/model-analysis/blob/v0.21.1/RELEASE.md)      |1.15 / 2.1    |2.17.0          |
|[0.21.0](https://github.com/tensorflow/model-analysis/blob/v0.21.0/RELEASE.md)      |1.15 / 2.1    |2.17.0          |
|[0.15.4](https://github.com/tensorflow/model-analysis/blob/v0.15.4/RELEASE.md)      |1.15 / 2.0    |2.16.0          |
|[0.15.3](https://github.com/tensorflow/model-analysis/blob/v0.15.3/RELEASE.md)      |1.15 / 2.0    |2.16.0          |
|[0.15.2](https://github.com/tensorflow/model-analysis/blob/v0.15.2/RELEASE.md)      |1.15 / 2.0    |2.16.0          |
|[0.15.1](https://github.com/tensorflow/model-analysis/blob/v0.15.1/RELEASE.md)      |1.15 / 2.0    |2.16.0          |
|[0.15.0](https://github.com/tensorflow/model-analysis/blob/v0.15.0/RELEASE.md)      |1.15          |2.16.0          |
|[0.14.0](https://github.com/tensorflow/model-analysis/blob/v0.14.0/RELEASE.md)      |1.14          |2.14.0          |
|[0.13.1](https://github.com/tensorflow/model-analysis/blob/v0.13.1/RELEASE.md)      |1.13          |2.11.0          |
|[0.13.0](https://github.com/tensorflow/model-analysis/blob/v0.13.0/RELEASE.md)      |1.13          |2.11.0          |
|[0.12.1](https://github.com/tensorflow/model-analysis/blob/v0.12.1/RELEASE.md)      |1.12          |2.10.0          |
|[0.12.0](https://github.com/tensorflow/model-analysis/blob/v0.12.0/RELEASE.md)      |1.12          |2.10.0          |
|[0.11.0](https://github.com/tensorflow/model-analysis/blob/v0.11.0/RELEASE.md)      |1.11          |2.8.0           |
|[0.9.2](https://github.com/tensorflow/model-analysis/blob/v0.9.2/RELEASE.md)        |1.9           |2.6.0           |
|[0.9.1](https://github.com/tensorflow/model-analysis/blob/v0.9.1/RELEASE.md)        |1.10          |2.6.0           |
|[0.9.0](https://github.com/tensorflow/model-analysis/blob/v0.9.0/RELEASE.md)        |1.9           |2.5.0           |
|[0.6.0](https://github.com/tensorflow/model-analysis/blob/v0.6.0/RELEASE.md)        |1.6           |2.4.0           |

## Questions

Please direct any questions about working with TFMA to
[Stack Overflow](https://stackoverflow.com) using the
[tensorflow-model-analysis](https://stackoverflow.com/questions/tagged/tensorflow-model-analysis)
tag.


