fffupeng的博客

tensorflow 提供很多api，最低级的api tensorflow Core给你提供完整的编程控制，这时我们应该关注的。高层的api是建立在tensorflow core之上。A high-level API like tf.contrib.learn helps you manage data sets, estimators, training and inference.  下

#coding=utf8import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data\\", one_hot=True)#构建计算图x = tf.placeholder(tf.float32,[None,78

#coding=utf8 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('MNIST_data',one_hot=True) def weight_variable(shape): initial =

#coding=utf8 #author by fffupeng #envirnment anaconda python 3.5 windows #这是一个将mnist中的卷积改成mobilenet的思想 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = inp