u012073033的专栏

bert server 搭建

Loss function L:input:a function, output :how bad it is;L(f) = L(w,b)lossfunction：可以衡量一组参数的好坏。函数的目标是：找到一组使得loss最小的w和b。方法为：gradient descent...

tf.constant_initializer : 将变量初始化为常量。eg: >>> import numpy as np >>> import tensorflow as tf >>> value = [0, 1, 2, 3, 4, 5, 6, 7] >>> init = tf.constant_i...

模型保存和还原都是通过TensorFlow的一个API实现的，这个API就是tf.train.saver类 保存模型 eg:import tensorflow as tf#声明两个变量并计算他们的和v1 = tf.Variable(tf.constant(1.0,shape=[1],name="v1"))v2 = tf.Variable(tf.constant(2.0,shape=...

1、tf.multiply(x,y) 对应元素相乘x: 一个类型为:half, float32, float64, uint8, int8, uint16, int16, int32, int64, complex64, complex128的张量。y: 一个类型跟张量x相同的张量。返回值： x * y element-wise.import tensorflow as tf...

1decode_csv读取数据import tensorflow as tf#创建文件队列filenames ['./s0000025_1.csv','./s0000025_2.csv']filename_queue = tf.train.string_input_producer(filenames,shuffle=True)#shuffle=True 文件队列随机读取，默认...