TF随笔-7
来源:互联网 发布:code.org 是什么软件 编辑:程序博客网 时间:2024/06/14 09:21
求平均值的函数
reduce_mean
axis为1表示求行
axis为0表示求列
>>> xxx=tf.constant([[1., 10.],[3.,30.]])>>> sess.run(xxx)
array([[ 1., 10.],
[ 3., 30.]], dtype=float32)
>>> mymean=tf.reduce_mean(xxx,0)
>>> sess.run(mymean)
array([ 2., 20.], dtype=float32)
>>> mymean=tf.reduce_mean(xxx,1)
>>> sess.run(mymean)
array([ 5.5, 16.5], dtype=float32)
>>>
keep_dims表示是否保持维度。
>>> sess.run(mymean)
array([[ 2., 20.]], dtype=float32)
>>> mymean=tf.reduce_mean(xxx,axis=0,keep_dims=False)
>>> sess.run(mymean)
array([ 2., 20.], dtype=float32)
>>> mymean=tf.reduce_mean(xxx,keep_dims=False)
>>> sess.run(mymean)
11.0
>>> mymean=tf.reduce_mean(xxx,keep_dims=True)
>>> sess.run(mymean)
array([[ 11.]], dtype=float32)
>>> mymean=tf.reduce_mean(xxx)
>>> sess.run(mymean)
11.0
tf.reduce_mean
reduce_mean(
input_tensor,
axis=None,
keep_dims=False,
name=None,
reduction_indices=None
)
Defined in tensorflow/python/ops/math_ops.py
.
See the guide: Math > Reduction
Computes the mean of elements across dimensions of a tensor.
Reduces input_tensor
along the dimensions given in axis
. Unless keep_dims
is true, the rank of the tensor is reduced by 1 for each entry in axis
. If keep_dims
is true, the reduced dimensions are retained with length 1.
If axis
has no entries, all dimensions are reduced, and a tensor with a single element is returned.
For example:
# 'x' is [[1., 1.]
# [2., 2.]]
tf.reduce_mean(x) ==> 1.5
tf.reduce_mean(x, 0) ==> [1.5, 1.5]
tf.reduce_mean(x, 1) ==> [1., 2.]
Args:
input_tensor
: The tensor to reduce. Should have numeric type.axis
: The dimensions to reduce. IfNone
(the default), reduces all dimensions.keep_dims
: If true, retains reduced dimensions with length 1.name
: A name for the operation (optional).reduction_indices
: The old (deprecated) name for axis.
tf.pow
pow(
x,
y,
name=None
)
Defined in tensorflow/python/ops/math_ops.py
.
See the guide: Math > Basic Math Functions
Computes the power of one value to another.
Given a tensor x
and a tensor y
, this operation computes \\(x^y\\) for corresponding elements in x
and y
. For example:
# tensor 'x' is [[2, 2], [3, 3]]
# tensor 'y' is [[8, 16], [2, 3]]
tf.pow(x, y) ==> [[256, 65536], [9, 27]]
class tf.train.AdamOptimizer
__init__(learning_rate=0.001, beta1=0.9, beta2=0.999, epsilon=1e-08, use_locking=False, name='Adam')
#!/usr/bin/env python2# -*- coding: utf-8 -*-"""Created on Mon Jul 10 09:35:04 2017@author: myhaspl@myhaspl.com,http://blog.csdn.net/myhaspl"""import tensorflow as tfimport numpy as npbatch_size=10w1=tf.Variable(tf.random_normal([2,3],stddev=1,seed=1))w2=tf.Variable(tf.random_normal([3,1],stddev=1,seed=1))x=tf.placeholder(tf.float32,shape=(None,2),name="x")y=tf.placeholder(tf.float32,shape=(None,1),name="y")h=tf.matmul(x,w1)yo=tf.matmul(h,w2)#损失函数计算差异平均值cross_entropy=tf.reduce_mean(tf.abs(y-yo))#反向传播train_step=tf.train.AdamOptimizer().minimize(cross_entropy)#生成200个随机样本DATASIZE=200x_=np.random.rand(DATASIZE,2)y_=[[int((x1+x2)>2.5)] for (x1,x2) in x_]with tf.Session() as sess: #初始化变量 init_op=tf.global_variables_initializer() sess.run(init_op) print sess.run(w1) print sess.run(w2) #设定训练轮数 TRAINCOUNT=10000 for i in range(TRAINCOUNT): #每次递进选择一组 start=(i*batch_size) % DATASIZE end=min(start+batch_size,DATASIZE) #开始训练 sess.run(train_step,feed_dict={x:x_[start:end],y:y_[start:end]}) if i%1000==0: total_cross_entropy=sess.run(cross_entropy,feed_dict={x:x_[start:end],y:y_[start:end]}) print("%d 次训练之后,损失:%g"%(i+1,total_cross_entropy)) print(sess.run(w1)) print(sess.run(w2))
[[-0.81131822 1.48459876 0.06532937 -2.4427042 0.0992484 0.59122431]
[ 0.59282297 -2.12292957 -0.72289723 -0.05627038 0.64354479 -0.26432407]]
[[-0.81131822]
[ 1.48459876]
[ 0.06532937]
[-2.4427042 ]
[ 0.0992484 ]
[ 0.59122431]]
1 次训练之后,损失:2.37311
1001 次训练之后,损失:0.587702
2001 次训练之后,损失:0.00187977
3001 次训练之后,损失:0.000224713
4001 次训练之后,损失:0.000245593
5001 次训练之后,损失:0.000837345
6001 次训练之后,损失:0.000561878
7001 次训练之后,损失:0.000521504
8001 次训练之后,损失:0.000369141
9001 次训练之后,损失:2.88023e-05
[[-0.40749896 0.74481744 -1.35231423 -1.57555723 1.5161525 0.38725093]
[ 0.84865922 -2.07912779 -0.41053897 -0.21082011 -0.0567192 -0.69210052]]
[[ 0.36143586]
[ 0.34388798]
[ 0.79891819]
[-1.57640576]
[-0.86542428]
[-0.51558757]]
tf.nn.relu
relu(
features,
name=None
)
Defined in tensorflow/python/ops/gen_nn_ops.py
.
See the guides: Layers (contrib) > Higher level ops for building neural network layers, Neural Network > Activation Functions
Computes rectified linear: max(features, 0)
- TF随笔-7
- TF随笔-2
- tf随笔-1
- TF随笔-3
- TF随笔-4
- tf随笔-5
- tf随笔-6
- TF随笔-8
- TF随笔-9
- TF随笔-10
- TF随笔-11
- TF随笔-12
- TF随笔-13
- TF随笔-14-二分法求解一元方程
- tf随笔-15 正则化+指数衰减+滑动平均
- TF
- tf
- 随笔7
- 基本概念 Basic concepts
- 剑指offer面试题51 数组中重复的数字
- VS2015中”This function or variable may be unsafe.”警告的解决办法
- 多重背包-可行性poj1742
- android蓝牙开发入门
- TF随笔-7
- Shape 圆弧问题
- Android零基础入门第6节:配置优化SDK Manager,正式约会女神
- leetcode 7 Reverse Integer
- iOS之ReactiveCocoa入门教程
- LeetCode#14 Longest Common Prefix
- 网站服务器端的软件优化方案
- 华尔街量化策略全线遭重创 “标杆”文艺复兴基金六月大跌
- What really happens when you navigate to a URL