python机器学习-Python TensorFlow

import tensorflow as tf  
  
# Change type of data  
type_float = tf.constant(3.123456789, tf.float32)  
type_int = tf.cast(type_float, dtype=tf.int32)  
print(type_float.dtype)  
print(type_int.dtype)   

以下是一些可用于处理tensor 的数学函数

• tensorflow.add(a, b)
• tensorflow.substract(a, b)
• tensorflow.multiply(a, b)
• tensorflow.div(a, b)
• tensorflow.pow(a, b)
• tensorflow.exp(a)
• tensorflow.sqrt(a)

import tensorflow as tf  
  
x = tf.constant([2.0], dtype = tf.float32)  
tensor_a = tf.constant([[1,2]], dtype = tf.int32)  
tensor_b = tf.constant([[3, 4]], dtype = tf.int32)  
  
#Sqaure Root  
print(tf.sqrt(x))  
#Exponential  
print(tf.exp(x))  
#Power  
print(tf.pow(x,x))  
#Add  
tensor_add = tf.add(tensor_a, tensor_b)  
print(tensor_add)  
#Substarct  
tensor_sub = tf.subtract(tensor_a, tensor_b)  
print(tensor_sub)  
#Multiply  
tensor_mul = tf.multiply(tensor_a, tensor_b)  
print(tensor_mul)  
#Divide  
tensor_div = tf.div(tensor_a, tensor_b)  
print(tensor_div)  

上面的代码，演示了上面提到的所有TensorFlow函数的使用0

TensorFlow 变量

要在 TensorFlow 中创建变量，我们使用 tensorflow.get_variable()

句法

import tensorflow as tf  
  
# Create a Variable  
var = tf.get_variable("var", [1, 2])  
print(var)  
  
#following initializes the variable with a initial/default value  
var_init_1 = tf.get_variable("var_init_1", [1, 2], dtype=tf.int32,  initializer=tf.zeros_initializer)  
print(var_init_1)         
  
#Initializes the first value of the tensor equals to tensor_const  
tensor_const = tf.constant([[10, 20],[30, 40]])  
var_init_2 = tf.get_variable("var_init_2", dtype=tf.int32,  initializer=tensor_const)  
print(var_init_2)     

上面代码的输出将是 <tf.Variable ‘var:0’ shape=(1, 2) dtype=float32_ref> <tf.Variable ‘var_init_1:0’ shape=(1, 2) dtype=int32_ref> <tf .Variable ‘var_init_2:0’ shape=(2, 2) dtype=int32_ref>

TensorFlow 占位符

占位符的目的是提供tensor。占位符用于初始化数据以在tensor内流动。要提供占位符，您需要使用方法 feed_dict。占位符将仅在会话中提供。

句法

tf.placeholder(dtype,shape=None,name=None)

论据：

import tensorflow as tf  
data_placeholder_a = tf.placeholder(tf.float32, name = "data_placeholder_a")  
print(data_placeholder_a)  

上面代码的输出将是 Tensor(“data_placeholder_a:0”, dtype=float32)

TensorFlowSession

下面我们将演示使用 TensorFlow Session

import tensorflow as tf  
  
## Create, run  and evaluate a session  
x = tf.constant([2])  
y = tf.constant([4])              
  
## Create operator  
multiply = tf.multiply(x, y)  
  
## Create a session to run the code  
sess = tf.Session()  
result_1 = sess.run(multiply)  
print(result_1)  
sess.close()  

上述代码的输出将是 [8]

简单的 Python Tensorflow 程序

import numpy as np  
import tensorflow as tf 

在上面的代码中，我们导入了 numpy 和 TensorFlow，并将它们分别重命名为 np 和 tf。

X_1 = tf.placeholder(tf.float32, name = "X_1")  
X_2 = tf.placeholder(tf.float32, name = "X_2")  

multiply = tf.multiply(X_1, X_2, name = "multiply")  

with tf.Session() as session:    
    result = session.run(multiply, feed_dict={X_1:[1,2,3], X_2:[4,5,6]})    
    print(result)   

import numpy as np  
import tensorflow as tf  
  
X_1 = tf.placeholder(tf.float32, name = "X_1")  
X_2 = tf.placeholder(tf.float32, name = "X_2")  
  
multiply = tf.multiply(X_1, X_2, name = "multiply")  
  
with tf.Session() as session:  
    result = session.run(multiply, feed_dict={X_1:[1,2,3], X_2:[4,5,6]})  
    print(result)  

## Numpy to pandas    
import numpy as np    
import pandas as pd  
  
h = [[1,2],[3,4]]     
df_h = pd.DataFrame(h)    
print('Data Frame:', df_h)    
    
## Pandas to numpy    
df_h_n = np.array(df_h)    
print('Numpy array:', df_h_n)    

import numpy as np  
import tensorflow as tf  
x_input = np.random.sample((1,2))  
print(x_input) 

x = tf.placeholder(tf.float32, shape=[ 1 , 2 ], name =  'X' )  

dataset = tf.data.Dataset.from_tensor_slices(x)  

iterator = dataset.make_initializable_iterator()   
get_next = iterator.get_next()  

with tf.Session() as sess:  
    # feed the placeholder with data  
    sess.run(iterator.initializer, feed_dict={ x: x_input })   
    print(sess.run(get_next)) # output [ 0.52374458  0.71968478] 

import numpy as np  
import tensorflow as tf  
x_input = np.random.sample((1,2))  
print(x_input)  
# using a placeholder  
x = tf.placeholder(tf.float32, shape=[1,2], name = 'X')  
dataset = tf.data.Dataset.from_tensor_slices(x)  
iterator = dataset.make_initializable_iterator()   
get_next = iterator.get_next()  
with tf.Session() as sess:  
    # feed the placeholder with data  
    sess.run(iterator.initializer, feed_dict={ x: x_input })   
    print(sess.run(get_next))