tensorflow编程实战

TensorFlow编程实战

---

一，tf.constant() and so on

• tf.constant(value,share,dtpye,name,verify_shape)
• value:初始化值
• shape:n1n2n…nk(0<k<)
• verify_shape ?
• tf.zeros()
• tf.ones()
• tf.ones_like()
• tf.fill()
• tf.lin_space(start,end,num,name)
• tf.range(start,limit,delta,dtype,name)

二，tensorflow random generate constant

• tf.random_normal()
• tf.truncated_normal()
• tf.random_uniform()
• tf.random_shuffle()
• tf.multinomil()
• tf.random_gamma()

三，Operations

• elements-wise mathematical operations,like Add,Equal
• array operations,like concat,shuffle
• matrix operations,like MatrixMul,
• stateful operations,like Variables
• netural network building block,like Softmax,Sigmoid,MaxPool
• checking Point operations,like save Restore
• Queue and synchronization operations,like Enqueue,MutexAcquire
• control flow operations,like Merge,Switch,Enter,NextIteration,Leave

四，Tensor DataType

• tf.(b)float_(16/32/64)
• tf.complex(64/128)
• tf.uint(8/16)
• tf.int(8/16/32/64)
• bool
• string
• tf.qint(8/16/32)
• tf.quint(8/16)
• tf.resource

五，Tensor Varible

• tf.variable()
• tf.get_variable(name,shape,initicalizer)
• initial all the variable at once

with tf.Session() as sess:
		sess.run(tf.global_variables_initializer())

or
with tf.Session() as sess:
		sess.run(tf.variables_initializer(name1,name2,...))

六，Traning phrase1

1. reading data
2. create placeholders for input and labels
3. create weight and bias
4. Y_predicted=wX+b
5. specify loss function:loss=tf.Square(Y-Y_predicted,name)
6. create optimizer:

opt=tf.train.GrandientDecentOptimizer(learning_rate=0.01)
optimizer=opt.minimize(loss)

or

optimizer=tf.train.GradientDecentOptimizer(learnint_rate=0.001).minimize(loss)
sess.run([optimizer,loss],feedDict={X:x,Y:y})

7. optimizer list,like AdagradOptimizer,MomemtuOptimizer…

七，Traning Phrase2

1. initialize variables
2. run optimizer:usually use feed_Dict()
3. write log files as FileWriter
4. see it on TensorBoard

tips

1. tensor objects are not iterable