博客
关于我
深度学习TF—2.TensorFlow2高阶操作
阅读量:245 次
发布时间:2019-03-01

本文共 1569 字,大约阅读时间需要 5 分钟。

TensorFlow????

???????

1. tf.concat: ??????????

concat????????????????????????????????

2. tf.stack: ???????

tf.stack????????????????????????????

3. tf.unstack: ?????

unstack?????????????????????????????????????

4. tf.split: ???????

split????????????????????????????


????????

1. tf.norm: ????

?????????????????

2. tf.reduce_max/min/mean/sum: ?????????????

??????????????????

3. tf.argmax/argmin: ????????????

????????????????

4. tf.equal: ????

??????????????????????

5. tf.unique: ????????

??????????


??????

1. tf.sort/tf.argsort: ?????

sort??????????argsort???????????

2. tf.math.top_k: ???????k?

?????k???????????


???????

1. tf.pad: ????

pad???????????????????????????

2. tf.tile: ????

?????????????????


???????

1. tf.clip_by_value: ???????

???????????????

2. tf.clip_by_norm: ????????

??????????????

3. tf.nn.relu: ReLU????

????????????

4. tf.clip_by_global_norm: ??????

?????????????????


??????

1. tf.where: ??????

????????????????

2. tf.scatter_nd: ????????

??????????????

3. tf.meshgrid: ?????

?????????????????


??

1. tf.meshgrid ??

import tensorflow as tfimport matplotlib.pyplot as pltdef fun(x):    z = tf.math.sin(x[...,0]) + tf.math.sin(x[...,1])    return zx = tf.linspace(0., 2*3.14, 500)y = tf.linspace(0., 2*3.14, 500)point_x, point_y = tf.meshgrid(x, y)points = tf.stack([point_x, point_y], axis=2)print(points.shape)z = fun(points)plt.figure('plot 2d func value')plt.imshow(z, origin='lower', interpolation='none')plt.colorbar()plt.figure('plot 2d func contour')plt.contour(point_x, point_y, z)plt.colorbar()plt.show()

??????????????????????????????????

转载地址:http://uzsv.baihongyu.com/

你可能感兴趣的文章
Pandas进阶大神!从0到100你只差这篇文章!
查看>>
spring5-介绍Spring框架
查看>>
Pandas:将一列与数据帧的所有其他列进行比较
查看>>
PandoraFMS 监控软件 SQL注入漏洞复现
查看>>
PandoraFMS 监控软件 任意文件上传漏洞复现
查看>>
Parallel.ForEach的基础使用
查看>>
parallels desktop for mac安装虚拟机 之parallelsdesktop密钥 以及 parallels desktop安装win10的办公推荐可以提高办公效率...
查看>>
paramiko模块
查看>>
param[:]=param-lr*param.grad/batch_size的理解
查看>>
Spring Cloud 之注册中心 EurekaServerAutoConfiguration源码分析
查看>>
ParseChat应用源码ios版
查看>>
Part 2异常和错误
查看>>
Spring @Async执行异步方法的简单使用
查看>>
PAT 1027 Colors in Mars
查看>>
PAT 1127 ZigZagging on a Tree[难]
查看>>
PAT 2-07. 素因子分解(20)
查看>>
PAT-1044. Shopping in Mars (25)
查看>>
PAT-乙级-1040 有几个PAT
查看>>
PAT1093 Count PAT's (25)(逻辑题)
查看>>
PATA1038题解(需复习)
查看>>