tf.maximum

site/en/api_docs/api_docs/python/tf/maximum.md

maximum(x,y,name=None
)

Defined in tensorflow/python/ops/gen_math_ops.py.
See the guide: Math > Basic Math Functions

Returns the max of x and y (i.e. x > y ? x : y) element-wise.
返回最大值 (x > y ? x : y)。

element-wise：逐个元素，按元素

1. Args

x: A Tensor. Must be one of the following types: half, float32, float64, int32, int64.
y: A Tensor. Must have the same type as x.
name: A name for the operation (optional).

2. Returns

A Tensor. Has the same type as x.

3. example

#!/usr/bin/env python
# -*- coding: utf-8 -*-from __future__ import absolute_import
from __future__ import division
from __future__ import print_functionimport tensorflow as tf
import numpy as npinput = [1, 3, 5, 7, 9]f1 = tf.maximum(input, 5)
f2 = tf.minimum(input, 5)
f3 = tf.argmax(input, 0)
f4 = tf.argmin(input, 0)with tf.Session() as sess:print(sess.run(f1))print(sess.run(f2))print(sess.run(f3))print(sess.run(f4))

/usr/bin/python2.7 /home/strong/git_workspace/MonoGRNet/yongqiang.py
2019-07-08 21:53:25.317950: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-07-08 21:53:25.403899: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-07-08 21:53:25.404138: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7335
pciBusID: 0000:01:00.0
totalMemory: 7.92GiB freeMemory: 7.46GiB
2019-07-08 21:53:25.404148: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
[5 5 5 7 9]
[1 3 5 5 5]
4
0Process finished with exit code 0

tf.maximum相关推荐

一文搞懂tf.function
朋友们,如需转载请标明出处:https://blog.csdn.net/jiangjunshow 在tensorflow1.x的时候,代码默认的执行方式是graph execution(图执行),而从 ...
tf.maximun(a,b)_tf.minimum(a,b)
tf.maximum:用法tf.maximum(a,b),返回的是a,b之间的最大值, tf.miniimum:用法tf.miiinimum(a,b),返回的是a,b之间的最小值, tf.argmax ...
API pytorch tensorflow
pytorch与tensorflow API速查表方法名称 pytroch tensorflow numpy 裁剪 torch.clamp(x, min, max) tf.clip_by_value ...
PyTorch全连接ReLU网络
PyTorch全连接ReLU网络 1．PyTorch的核心是两个主要特征: • 一个n维张量,类似于numpy,但可以在GPU上运行 • 搭建和训练神经网络时的自动微分/求导机制本文将使用全连接的R ...
【TensorFlow2.0】(7) 张量排序、填充、复制、限幅、坐标选择
各位同学好,今天和大家分享一下TensorFlow2.0中的一些操作.内容有: (1)排序 tf.sort().tf.argsort().top_k():(2)填充 tf.pad():(3)复制 tf ...
DeepMind提图像生成的递归神经网络DRAW，158行Python代码复现
作者 | Samuel Noriega 译者 | Freesia 编辑 | 夕颜出品 | AI科技大本营(ID: rgznai100) [导读]最近,谷歌 DeepMInd 发表论文( DRAW: ...
输入示例，自动生成代码：TensorFlow官方工具TF-Coder已开源
视学算法报道编辑:魔王.陈萍转载自公众号:机器之心如何使编程更加便捷?最近,谷歌 TensorFlow 开源了一个帮助开发者写 TensorFlow 代码的程序合成工具 TF-Coder. 项目 ...
手把手教你实现GAN半监督学习
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达引言本文主要介绍如何在tensorflow上仅使用200个带标 ...
学习笔记CB013: TensorFlow、TensorBoard、seq2seq
2019独角兽企业重金招聘Python工程师标准>>> tensorflow基于图结构深度学习框架,内部通过session实现图和计算内核交互. tensorflow基本数学运算用法 ...
如何使用TensorFlow和VAE模型生成手写数字
全部 VAE 代码:https://github.com/FelixMohr/Deep-learning-with-Python/blob/master/VAE.ipynb 自编码器是一种能够用来学习 ...

tf.maximum

tf.maximum

1. Args

2. Returns

3. example

tf.maximum相关推荐

最新文章

热门文章