1.利用PyCharm創(chuàng)建TensorFlow程序（TensorFlow 1.1.0)
bogon:~ onefish$ python
>>> import tensorflow as tf
>>> print tf.__version__
1.1.0
#encoding:utf-8
import tensorflow as tf
import numpy as np
def add_layer(inputs,in_size,out_size,n_layer,activation_function=None):
layer_name="layer%s" % n_layer
with tf.name_scope(layer_name):
with tf.name_scope('weights'):
Weights = tf.Variable(tf.random_normal([in_size,out_size]))
tf.summary.histogram(layer_name+"/weights",Weights)
with tf.name_scope('biases'):
biases = tf.Variable(tf.zeros([1,out_size])+0.1)
tf.summary.histogram(layer_name+"/biases",biases) #可視化觀看變量
with tf.name_scope('Wx_plus_b'):
Wx_plus_b = tf.matmul(inputs,Weights)+biases #inputs*Weight+biases
tf.summary.histogram(layer_name+"/Wx_plus_b",Wx_plus_b) #可視化觀看變量
if activation_function is None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b)
tf.summary.histogram(layer_name+"/outputs",outputs) #可視化觀看變量
return outputs
#創(chuàng)建數(shù)據(jù)x_data砰识，y_data
x_data = np.linspace(-1,1,300)[:,np.newaxis] #[-1,1]區(qū)間脂信，300個單位，np.newaxis增加維度
noise = np.random.normal(0,0.05,x_data.shape) #噪點
y_data = np.square(x_data)-0.5+noise
with tf.name_scope('inputs'): #結構化
xs = tf.placeholder(tf.float32,[None,1],name='x_input')
ys = tf.placeholder(tf.float32,[None,1],name='y_input')
#三層神經剥险，輸入層（1個神經元）聪蘸，隱藏層（10神經元），輸出層（1個神經元）
l1 = add_layer(xs,1,10,n_layer=1,activation_function=tf.nn.relu) #隱藏層
prediction = add_layer(l1,10,1,n_layer=2,activation_function=None) #輸出層
#predition值與y_data差別
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1])) #square()平方,sum()求和,mean()平均值
tf.summary.scalar('loss',loss) #可視化觀看常量
with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss) #0.1學習效率,minimize(loss)減小loss誤差
init = tf.global_variables_initializer()
sess = tf.Session()
#合并到Summary中
merged = tf.summary.merge_all()
#選定可視化存儲目錄
writer = tf.summary.FileWriter("~/Desktop/",sess.graph)
sess.run(init) #先執(zhí)行init
#訓練1k次
for i in range(1000):
sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
if i%50==0:
result = sess.run(merged,feed_dict={xs:x_data,ys:y_data}) #merged也是需要run的
writer.add_summary(result,i) #result是summary類型的表制，需要放入writer中健爬，i步數(shù)（x軸）
2.在PyCharm中運行該程序，運行結果如下
/Users/onefish/anaconda/bin/python /Users/onefish/Python/TFtest/FirstTF.py
2017-06-14 15:31:07.786890: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786910: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786914: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786919: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786923: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
Process finished with exit code 0
3.運行結束后么介，可以通過PyCharm自帶的console執(zhí)行TensorBoard命令去讀取log文件娜遵。
這里需要注意的是log文件存放的位置，并不是在系統(tǒng)的~/Desktop/壤短，運行之后在項目中生成了一個Desktop的文件夾设拟，如圖：
WX20170614-163309@2x.png
4.在PyCharm中運行
onefish:TFtest onefish$ tensorboard --logdir=/Users/onefish/Python/TFtest/Desop
WX20170614-163740@2x.png
5.訪問127.0.0.1:6006
WX20170614-163907@2x.png
