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_import from __future__ import division from __future__ import print_function import gzip import os import tempfile import n...

网络模型及测试图片放在一个文件夹下面#coding=utf-8 import tensorflow as tf import scipy.io import scipy.misc import os import numpy as np import matplotlib.pyplot as plt def nets(data_path,input_img): layers = ( ...

tf的变量和常量操作#coding=utf-8 import tensorflow as tf state = 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-8 import numpy as np from comtypes.npsupport import numpy from __builtin__ import xrange def Sigmod(x, diver = False): if(diver == True): ...