Step1 新增清華映象，加快下載速度, 建立tensorflow-gpu環境

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --set show_channel_urls yes

conda create -n tensorflow-gpu python=3.6
source activate tensorflow-gpu #（linux下+source， windows下無需+source）

Step2 安裝tensorflow-gpu

conda install tensorflow-gpu

Step3 安裝keras-gpu

conda install keras-gpu

注意：一定要加上-gpu，否則系統會預設成cpu

Step4 驗證是gpu還是cpu

• 預設gpu

import tensorflow as tf
# Creates a graph.
a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')
b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3
 
, 2], name='b')
c = tf.matmul(a, b)
# Creates a session with log_device_placement set to True.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))
# Runs the op.
print(sess.run(c))

• 手動設定gpu與cpu

# Creates a graph.
import tensorflow as tf
with tf.device('/cpu:0'):
  a = tf.constant([1.0
 
, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')
  b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name='b')
c = tf.matmul(a, b)
# Creates a session with log_device_placement set to True.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))
# Runs the op.
print(sess.run(c))

若成功執行Gpu則在終端會有相應的gpu提示提示，例如：/gpu: 0 如下圖：