tf.nn.conv2d用法简介
来源:互联网 发布:java有哪些框架 编辑:程序博客网 时间:2024/05/22 03:11
tf.nn.conv2d(1.3.0版本)
#-*- coding:utf-8 -*-import numpy as npimport tensorflow as tf # 生成大小为[1,5,5,3]的输入图像batch = 1in_height = in_width = 5in_channels = 3input = tf.constant(1.0, shape=[batch, in_height, in_width, in_channels])# 生成大小为[3,3,3,1]的卷积核filter_width = filter_height = 3filter = tf.constant(1.0, shape=[filter_width, filter_height, in_channels, 1])# 卷积运算output1 = tf.nn.conv2d(input, filter, strides=[1,2,2,1], padding="SAME", name="conv1")output2 = tf.nn.conv2d(input, filter, strides=[1,2,2,1], padding="VALID", name="conv2")# 显示输出图像尺寸print("output1: %s" %np.shape(output1))print("output2: %s" %np.shape(output2))
# 输出结果output1: (1, 3, 3, 1)output2: (1, 2, 2, 1)
阅读全文
0 0
- tf.nn.conv2d用法简介
- tf.nn.conv2d 实例
- tf.nn.conv2d()
- tf.nn.conv2d理解
- tf.nn.conv2d
- TensorFlow tf.nn.conv2d
- tf.nn.conv2d()
- tf.nn.conv2d
- TensorFlow-tf.nn.conv2d 函数
- Tensorflow系列:tf.nn.conv2d
- tf.nn.conv2d函数讲解
- TensorFlow tf.nn.conv2d()介绍
- tensorflow学习:tf.nn.conv2d 和 tf.layers.conv2d
- tf.layers.conv2d和tf.nn.conv2d使用区别
- Tensorflow -- tf.nn.conv2d() 函数详解
- tensorflow function笔记: tf.nn.conv2d
- 卷积操作 tensorflow tf.nn.conv2d
- tensorflow(二):tf.nn.conv2d
- jsp动作
- 约束理论
- 微信小程序--图片懒加载
- pyspark之数据处理学习【离群值】(3)
- 教你用深度学习LSTM网络预测流行音乐趋势(附代码)
- tf.nn.conv2d用法简介
- 十九、函数式编程
- Pythonjic基础‘姿势’4
- golang 工程结构与编译
- (一)spring-boot集成mybatis
- linux 查看进程 和杀死进程
- AndroidStudio相关内容
- 机器学习相关术语
- Linux学习笔记:文件的权限