TF基本概念
Graph 表示計算任務
Node 可以是Operation也可以是數據存儲容器
在session的context中執行graph
使用tensor表示數據
通過variable維護狀態
使用feed和fetch 爲任意操作賦值(arbitrary operation)或者從中獲取數據
Tensor 類似於numpy 中的數組
3# a rank 0 tensor; this is a scalar withshape []
[1. ,2., 3.] # a rank 1tensor; this is a vector with shape [3]
[[1., 2., 3.], [4., 5., 6.]] # a rank 2tensor; a matrix with shape [2, 3]
[[[1., 2., 3.]], [[7., 8., 9.]]] # a rank 3tensor with shape [2, 1, 3]
Computational Graph包括兩步
1、 Building the computational graph.
將TF操作轉換成Graph nodes的形式,每個node包括input Tensor 和 output Tensor;constant node 只有固定輸入沒有輸出
Eg:
import tensorflow as tf
node1 = tf.constant(3.0, tf.float32)
node2 = tf.constant(4.0) # also tf.float32 implicitly
print node1, node2
[out]
Tensor("Const:0", shape=TensorShape([]), dtype=float32)Tensor("Const_1:0", shape=TensorShape([]), dtype=float32)
sess = tf.Session()
print sess.run([node1,node2])
[out]
[3.0, 4.0]
將上述兩個node 相加產生新的node 並輸出computation graph
node3 = tf.add(node1, node2)
print "node3: ", node3
print "sess.run(node3):",sess.run(node3)
[out]
node3: Tensor("Add:0", shape=TensorShape([]), dtype=float32)
sess.run(node3): 7.0
Placeholders可以不需要在定義的時候賦值,可以隨後賦值
EG:
IN:
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
adder_node = a + b # + provides a shortcut for tf.add(a, b)
print sess.run(adder_node, {a: 3, b:4.5})
print sess.run(adder_node, {a: [1,3], b:[2, 4]})
OUT:
7.5
[ 3. 7.]
在此基礎上在加一個graph
IN:
add_add_triple = adder_node * 3.
print sess.run(add_add_triple,{a:3,b:4.5})
OUT:
22.5
2、Running thecomputational graph.
爲了計算node 值(3.0)(4.0)必須使用Session
Variables 可以將trainableparameters 加到graph中
構造Variable需要類型和初值
IN:
W = tf.Variable([.3], tf.float32)
b = tf.Variable([-.3], tf.float32)
x = tf.placeholder(tf.float32)
linear_model = W * x +b
#variable initialize needs call a specialoperation
init = tf.initialize_all_variables()
sess.run(init)
print sess.run(linear_model,{x:[1,2,3,4]})
OUT:
[ 0. 0.30000001 0.60000002 0.90000004]
計算loss func
IN:
############ y and calculate loss function
y = tf.placeholder(tf.float32)
squared_deltas = tf.square(linear_model -y)
loss = tf.reduce_sum(squared_deltas)
printsess.run(loss,{x:[1,2,3,5],y:[0,-1,-2,-3]})
OUT:
26.09
手動調參 tf.assign
####adjust the parametres by hand
IN:
fixW = tf.assign(W,[-1.])
fixb = tf.assign(b,[1.])
sess.run([fixW, fixb])
printsess.run(loss,{x:[1,2,3,4],y:[0,-1,-2,-3]})
OUT:
0.0
自動調參數gradient decent
IN:
#gradientDescent optimeze the parameter
optimizer =tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)
sess.run(init)
for i in range(1000):
sess.run(train,{x:[1,2,3,4],y:[0,-1,-2,-3]})
print sess.run([W,b])
[array([-0.9999969], dtype=float32),array([ 0.99999082], dtype=float32)]