luoganttcc的博客

#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Thu Mar 22 22:15:25 2018@author: luogan"""from tensorflow.examples.tutorials.mnist import input_datamnist=input_data.read_data_sets...

代码链接原文链接 github链接正确率有0.7左右

import tensorflow as tfinp = tf.Variable(tf.random_normal([1,5,5,5])) fil = tf.Variable(tf.random_normal([3,3,5,2])) op = tf.nn.conv2d(inp, fil, strides=[1, 2, 2, 1], padding='VALID') op1 = tf.n...

#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Sat Mar 24 16:35:11 2018@author: luogan"""'''from tensorflow.examples.tutorials.mnist import input_datamnist=input_data.read_data_...

区别SAME和VALIDVALIDinput = tf.Variable(tf.random_normal([1,5,5,5])) filter = tf.Variable(tf.random_normal([3,3,5,1])) op = tf.nn.conv2d(input, filter, strides=[1, 1, 1, 1], padding='VALID') ...

tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, data_format=None, name=None)官方教程说明：给定四维的input和filter tensor，计算一个二维卷积Args:input: A Tensor. type必须是以下几种类型之一: half, float32, f...

#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Thu Mar 22 22:15:25 2018@author: luogan"""from tensorflow.examples.tutorials.mnist import input_datamnist=input_data.re

    本文与上一篇文章有一点不同,就是中间的隐藏层由一层变成两层,在神经网络搭建的过程中,曾出现一点问题,就是正确率图突然变成0.11,通过调整隐藏节点的数量和W2的初值,正确率达到0.97,不如只有一层神经网络的结果神经网络并不是越深越好神经网络的结构应当接近与橄榄型对于ML而言,不宜多于五层#!/usr/bin/env python...

这是一个三层的神经网络,只含有一个隐藏层.正确率有98%#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Thu Mar 22 22:15:25 2018@author: luogan"""from tensorflow.examples.tutorials.mnist import input_da...

英文中文