commit | 6be604aaacd9d270de01c37ec6e9a9a077397848 | [log] [tgz] |
---|---|---|
author | Jared Duke <jdduke@google.com> | Tue Aug 04 12:26:02 2020 -0700 |
committer | TensorFlower Gardener <gardener@tensorflow.org> | Tue Aug 04 12:31:25 2020 -0700 |
tree | 9bc7f0b365c8e3195c29a32a78c2d6bd37c8a553 | |
parent | beab9b83eaf0a5227cc8c314726bb00a32c866ed [diff] |
Reland (Attempt #3) PR #35985: [TFLite int16] 16-bit version of ADD/SUB reference kernel operators Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/35985 This PR is one of steps to extend 8-bit quantization to support symmetric 16-bit activations. Each activation is of type int16 and symmetric around zero. The weight tensor precision remains at 8-bit signed values. The bias is set to int64 precision. In this PR we introduce implementation and tests for ADD/SUB kernel reference function. The specification of this operator: SUB Input 0: data_type : int16 range : [-32768, 32767] granularity: per-tensor, zero_point=0 Input 1: data_type : int16 range : [-32768, 32767] granularity: per-tensor, zero_point=0 Output 0: data_type : int16 range : [-32768, 32767] granularity: per-tensor, zero_point=0 ADD Input 0: data_type : int16 range : [-32768, 32767] granularity: per-tensor, zero_point=0 Input 1: data_type : int16 range : [-32768, 32767] granularity: per-tensor, zero_point=0 Output 0: data_type : int16 range : [-32768, 32767] granularity: per-tensor, zero_point=0 Copybara import of the project: -- b94cb4732ab536828e565fd1c7b557f124432e29 by Elena Zhelezina <elena.zhelezina@arm.com>: Added 16-bit version of ADD/SUB operators. Broadcasting is included. -- 924d0b72c568f249f2fd224a942f8922524bfede by Elena Zhelezina <elena.zhelezina@arm.com>: Addressed reviewer comments. -- dd0d9e8f03d1fb1b887609fffb8ea5a86638c63e by Elena Zhelezina <elena.zhelezina@arm.com>: Added versioning to ADD/SUB + some rework of the existing code. -- abae3fd9a9b894c07d13c9ef416092c9004bc913 by Elena Zhelezina <elena.zhelezina@arm.com>: Added versioning for ADD/SUB with new option in the schema.fbs schema_generated.h is edited manually. -- 24f3f5593a06d24fa1ca6be257f1265b5293d492 by Elena Zhelezina <elena.zhelezina@arm.com>: Fix for broken build. -- d252fe175aef3a1a08c65155815efb706aa80afd by Elena Zhelezina <elena.zhelezina@arm.com>: Fix for the failing internal test for NN delegates. -- 2223a5c380bb821eb05f8034703c687269353e32 by Elena Zhelezina <elena.zhelezina@arm.com>: Fix for asan failures. Change-Id: I2cf421ddda7f9e802202239136ab062bcd63b4aa -- 3c219a46ce5888e8e402b64cc943ac6522156ef5 by Elena Zhelezina <elena.zhelezina@arm.com>: Added broadcast params to addsub structure. Change-Id: I61d7d4a94087d052a782890799211031f6ed3015 -- 9131a38c776109cdbcfa60be602667ec7aafe00f by Elena Zhelezina <elena.zhelezina@arm.com>: Corrected defaults. Change-Id: I9ea50c75014cc03ac91fdef0f5b4fe11395f7074 PiperOrigin-RevId: 324865496
Documentation |
---|
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML-powered applications.
TensorFlow was originally developed by researchers and engineers working on the Google Brain team within Google's Machine Intelligence Research organization to conduct machine learning and deep neural networks research. The system is general enough to be applicable in a wide variety of other domains, as well.
TensorFlow provides stable Python and C++ APIs, as well as non-guaranteed backward compatible API for other languages.
Keep up-to-date with release announcements and security updates by subscribing to announce@tensorflow.org. See all the mailing lists.
See the TensorFlow install guide for the pip package, to enable GPU support, use a Docker container, and build from source.
To install the current release, which includes support for CUDA-enabled GPU cards (Ubuntu and Windows):
$ pip install tensorflow
A smaller CPU-only package is also available:
$ pip install tensorflow-cpu
To update TensorFlow to the latest version, add --upgrade
flag to the above commands.
Nightly binaries are available for testing using the tf-nightly and tf-nightly-cpu packages on PyPi.
$ python
>>> import tensorflow as tf >>> tf.add(1, 2).numpy() 3 >>> hello = tf.constant('Hello, TensorFlow!') >>> hello.numpy() b'Hello, TensorFlow!'
For more examples, see the TensorFlow tutorials.
If you want to contribute to TensorFlow, be sure to review the contribution guidelines. This project adheres to TensorFlow's code of conduct. By participating, you are expected to uphold this code.
We use GitHub issues for tracking requests and bugs, please see TensorFlow Discuss for general questions and discussion, and please direct specific questions to Stack Overflow.
The TensorFlow project strives to abide by generally accepted best practices in open-source software development:
Build Type | Status | Artifacts |
---|---|---|
Linux CPU | PyPI | |
Linux GPU | PyPI | |
Linux XLA | TBA | |
macOS | PyPI | |
Windows CPU | PyPI | |
Windows GPU | PyPI | |
Android | ||
Raspberry Pi 0 and 1 | Py3 | |
Raspberry Pi 2 and 3 | Py3 | |
Libtensorflow MacOS CPU | GCS | |
Libtensorflow Linux CPU | GCS | |
Libtensorflow Linux GPU | GCS | |
Libtensorflow Windows CPU | GCS | |
Libtensorflow Windows GPU | GCS |
Build Type | Status | Artifacts |
---|---|---|
Linux AMD ROCm GPU Nightly | Nightly | |
Linux AMD ROCm GPU Stable Release | Release 1.15 / 2.x | |
Linux s390x Nightly | Nightly | |
Linux s390x CPU Stable Release | Release | |
Linux ppc64le CPU Nightly | Nightly | |
Linux ppc64le CPU Stable Release | Release 1.15 / 2.x | |
Linux ppc64le GPU Nightly | Nightly | |
Linux ppc64le GPU Stable Release | Release 1.15 / 2.x | |
Linux aarch64 CPU Nightly Python 3.6 | Nightly | |
Linux aarch64 CPU Stable Release | Release 1.15 / 2.x | |
Linux CPU with Intel oneAPI Deep Neural Network Library (oneDNN) Nightly | Nightly | |
Linux CPU with Intel oneAPI Deep Neural Network Library (oneDNN) Stable Release | Release 1.15 / 2.x | |
Red Hat® Enterprise Linux® 7.6 CPU & GPU Python 2.7, 3.6 | 1.13.1 PyPI |
Learn more about the TensorFlow community and how to contribute.