TensorFlow
进程击序的媛
身体和灵魂,健身与学习,都在路上。
展开
-
一个例子训练神经网络(tenserflow)
import tensorflow as tf import numpy as np #create data x_data = np.random.randn(100) y_data = x_data*0.3 + 0.1 #create tensorflow structure start Weight = tf.Variable(tf.random_uniform([1], -1.0, ...原创 2018-04-10 21:50:43 · 448 阅读 · 0 评论 -
tf.Session
import tensorflow as tf import numpy as np matrix1 = tf.constant([[3,3]]) matrix2 = tf.constant([[2], [2]]) product = tf.matmul(matrix1, matrix2) # method1 sess = tf.Session() ...原创 2018-04-10 22:05:53 · 406 阅读 · 0 评论 -
Placeholder()传入值的应用
import tensorflow as tf import numpy as np input1 = tf.placeholder(tf.float32) input2 = tf.placeholder(tf.float32) output = tf.multiply(input1, input2) with tf.Session() as sess: print(sess.run(o...原创 2018-04-10 23:50:34 · 1082 阅读 · 0 评论 -
添加层add_layer()
import tensorflow as tf import numpy as np def add_layer(inputs, input_size, output_size, activation_function = None): Weights = tf.Variable(tf.random_normal([input_size, output_size])) biase...原创 2018-04-11 09:51:35 · 2900 阅读 · 0 评论 -
建造神经网络
import tensorflow as tf import numpy as np def add_layer(inputs, input_size, output_size, activation_function = None): Weights = tf.Variable(tf.random_normal([input_size, output_size])) biase...原创 2018-04-11 14:29:13 · 187 阅读 · 0 评论 -
结果可视化
import tensorflow as tf import numpy as np import matplotlib.pyplot as plt def add_layer(inputs, input_size, output_size, activation_function = None): Weights = tf.Variable(tf.random_normal([inpu...原创 2018-04-11 16:22:41 · 887 阅读 · 1 评论