dyh02016的博客

mnist数据集下载比较麻烦，用这个脚本方便一点，当然也可以自己提前下载好需要的数据集from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport gzipimport osimport tempfileimport n...

网络模型及测试图片放在一个文件夹下面#coding=utf-8import tensorflow as tfimport scipy.ioimport scipy.miscimport osimport numpy as npimport matplotlib.pyplot as pltdef nets(data_path,input_img): layers = ( ...

tf的变量和常量操作#coding=utf-8import tensorflow as tfstate = tf.Variable(0)delta = tf.constant(1)new_state = tf.add(state,delta)updata = tf.assign(state,new_state)init = tf.global_variables_initiali...

一开始学习深度学习的相关记录，涉及到前向传播和反向传播，看看最后的loss值是否会降低#coding=utf-8import numpy as npfrom comtypes.npsupport import numpyfrom __builtin__ import xrangedef Sigmod(x, diver = False): if(diver == True): ...