你需要一个64位版本的Python，在你的情况下，你使用的是32位版本。到目前为止，Tensorflow只支持64位版本的Python 3.5。X和3.8。Windows操作系统。请参阅安装文档以了解当前支持的内容

要检查您正在运行的Python版本，输入Python或python3启动解释器，然后输入import struct;print(struct.calcsize("P") * 8)，这将打印32或64来告诉您正在运行的Python的比特版本。

评论:

要下载不同版本的Windows Python，请访问python.org/downloads/windows并向下滚动，直到看到以“64”结尾的版本。这将是64位版本，应该与张量流一起工作

2.0兼容方案:

在终端(Linux/MacOS)或命令提示符(Windows)中执行以下命令，使用Pip安装Tensorflow 2.0:

#Install tensorflow using pip virtual env 
pip install virtualenv
virtualenv tf_2.0.0   # tf_2.0.0 is virtual env name
source tf_2.0.0/bin/activate
#You should see tf_2.0.0 Env now. Execute the below steps
pip install tensorflow==2.0.0
python
>>import tensorflow as tf
>>tf.__version__
2.0.0

在终端(Linux/MacOS)或命令提示符(Windows)中执行以下命令，使用Bazel安装Tensorflow 2.0:

git clone https://github.com/tensorflow/tensorflow.git
cd tensorflow

#The repo defaults to the master development branch. You can also checkout a release branch to build:
git checkout r2.0

#Configure the Build => Use the Below line for Windows Machine
python ./configure.py 

#Configure the Build => Use the Below line for Linux/MacOS Machine
./configure
#This script prompts you for the location of TensorFlow dependencies and asks for additional build configuration options. 

#Build Tensorflow package

#CPU support
bazel build --config=opt //tensorflow/tools/pip_package:build_pip_package 

#GPU support
bazel build --config=opt --config=cuda --define=no_tensorflow_py_deps=true //tensorflow/tools/pip_package:build_pip_package

试试这个:

export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-0.12.1-py3-none-any.whl
pip3 install --upgrade $TF_BINARY_URL

来源:https://www.tensorflow.org/get_started/os_setup(页面已不存在)

更新2/23/17 文档移至:https://www.tensorflow.org/install

我可以在我的Mac上安装tensorflow-macos和tensrflow-metal

$ python -m pip install -U pip
$ pip install tensorflow-macos
$ pip install tensorflow-metal

您需要使用正确版本的Python和pip。

在Windows 10上，使用Python 3.6。X版本我也面临同样的问题，然后在仔细检查后，我注意到我的64位机器上安装了Python-32位。记住TensorFlow只兼容64位的Python安装，不兼容32位的Python版本

如果我们从python.org下载Python，默认安装为32位。所以我们必须手动下载64位安装程序来安装Python 64位。然后将以下内容添加到PATH环境中。

C:\Users\AppData\Local\Programs\Python\Python36
C:\Users\AppData\Local\Programs\Python\Python36\Scripts

然后在命令提示符下执行gpupdate /Force。如果Python命令不能用于64位，则重新启动计算机。

然后在命令提示符下运行python。它应该显示64位。

C:\Users\YOURNAME>python
Python 3.6.3 (v3.6.3:2c5fed8, Oct  3 2017, 18:11:49) [MSC v.1900 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.

然后执行以下命令安装tensorflow CPU版本(推荐)

pip3 install --upgrade tensorflow

2020年10月更新:

Tensorflow现在支持Python 3.5。通过Python 3.8。X，但您仍然必须使用64位版本。

如果需要在同一台机器上运行多个版本的Python，可以使用虚拟环境来帮助管理它们。

我的环境:Win 10, python 3.6

pip3 install --upgrade tensorflow
pip install --upgrade tensorflow

错误:

> Collecting tensorflow Could not find a version that satisfies the
> requirement tensorflow (from versions: ) No matching distribution
> found for tensorflow

我还尝试了pip install tensorflow和pip install tensorflow-gpu。 但错误:

> Could not find a version that satisfies the requirement tensorflow (from versions: ) No matching distribution found for tensorflow
> Could not find a version that satisfies the requirement tensorflow-gpu (from versions: ) No matching distribution found for tensorflow-gpu

使用Step (https://www.tensorflow.org/install/install_windows)尝试安装OK

Follow the instructions on the Anaconda download site to download and install Anaconda. https://www.continuum.io/downloads Create a conda environment named tensorflow by invoking the following command: C:> conda create -n tensorflow pip python=3.5 Activate the conda environment by issuing the following command: C:> activate tensorflow (tensorflow)C:> # Your prompt should change Issue the appropriate command to install TensorFlow inside your conda environment. To install the CPU-only version of TensorFlow, enter the following command: (tensorflow)C:> pip install --ignore-installed --upgrade tensorflow To install the GPU version of TensorFlow, enter the following command (on a single line): (tensorflow)C:> pip install --ignore-installed --upgrade tensorflow-gpu