tensorflow學習:建立一個最簡單的神經網路
阿新 • • 發佈:2019-01-30
程式功能:使用y= x^2 - 0.5加噪聲生成1000個<x, y>樣本點,然後搭建一個最簡單的神經網路學習
import tensorflow as tf import numpy as np def add_layer(input_data, input_size, output_size, activation_function = None): ''' input_data:輸入資料 input_size:輸入的神經元個數 output_size:輸出的神經元個數 activation_function:激勵函式 ''' #產生input_size行output_size列的隨機數 Weights = tf.Variable(tf.random_normal([input_size, output_size])) #產生一行output_size列全為0.1的數 biases = tf.Variable(tf.zeros([1, output_size]) + 0.1) #input_data * weights + biases Wx_plus_b = tf.matmul(input_data, Weights) + biases if activation_function is None: output = Wx_plus_b else: output = activation_function(Wx_plus_b) return output #在-1到1之間均勻產生1000個數的list,並將其轉成列向量 x_data = np.linspace(-1, 1, 1000)[:, np.newaxis] noise = np.random.normal(0, 0.05, x_data.shape) y_data = np.square(x_data) - 0.5 + noise xs = tf.placeholder(tf.float32, [None, 1]) ys = tf.placeholder(tf.float32, [None, 1]) #隱藏層輸出10個神經單元,現在還不知道該怎麼設定這個神經單元數比較好 layer1 = add_layer(xs, 1, 10, tf.nn.relu) prediction = add_layer(layer1, 10, 1, None) #add_layer函式不需要自己實現,直接調下面函式也能達到相同的效果 # layer1_new = tf.layers.dense(xs, 10, tf.nn.relu) # prediction_new = tf.layers.dense(layer1_new, 1) #這兩個loss到底有什麼區別 loss = tf.reduce_mean(tf.square(ys - prediction)) # loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1])) train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss) init = tf.global_variables_initializer() with tf.Session() as sess: sess.run(init) for step in range(1001): #這個地方是用所有的資料進行梯度下降,這樣做不合適 sess.run(train_step, feed_dict = {xs: x_data, ys: y_data}) if step % 50 == 0: print(step, sess.run(loss, feed_dict = {xs: x_data, ys:y_data}))