1、TensorFlow安装
安装CPU版
pip install tensorflow
安装GPU版(支持CUDA的GPU卡)
pip install tensorflow-gpu
通过Conda虚拟环境安装CPU版TensorFlow
1）创建一个新的Conda虚拟环境
conda create -n tensorflow_cpu pip python=3.6
2）激活新创建的虚拟环境
activate tensorflow_cpu
激活后的效果：
(tensorflow_cpu) C:\Users\sglvladi>
3）在虚拟环境中执行安装
pip install --ignore-installed --upgrade tensorflow==1.9
通过Conda虚拟环境安装GPU版TensorFlow
1）创建一个新的Conda虚拟环境
conda create -n tensorflow_gpu pip python=3.6
2）激活新创建的虚拟环境
activate tensorflow_gpu
激活后的效果：
(tensorflow_gpu) C:\Users\sglvladi>
3）在虚拟环境中执行安装
pip install --ignore-installed --upgrade tensorflow-gpu==1.9
2、TensorFlow示例代码
>>> import tensorflow as tf
>>> tf.enable_eager_execution()
>>> tf.add(1, 2).numpy()
3
>>> hello = tf.constant('Hello, TensorFlow!')
>>> hello.numpy()
'Hello, TensorFlow!'
或
# Import `tensorflow` import tensorflow as tf # Initialize two constants x1 = tf.constant([1,2,3,4]) x2 = tf.constant([5,6,7,8]) # Multiply result = tf.multiply(x1, x2) # Print the result print(result)
或
# Import `tensorflow` import tensorflow as tf # Initialize two constants x1 = tf.constant([1,2,3,4]) x2 = tf.constant([5,6,7,8]) # Multiply result = tf.multiply(x1, x2) # Intialize the Session sess = tf.Session() # Print the result print(sess.run(result)) # Close the session sess.close()
或
# Import `tensorflow` import tensorflow as tf # Initialize two constants x1 = tf.constant([1,2,3,4]) x2 = tf.constant([5,6,7,8]) # Multiply result = tf.multiply(x1, x2) # Initialize Session and run `result` with tf.Session() as sess: output = sess.run(result) print(output)