《TensorFlow机器学习实战指南》学习笔记三

用TensorFlow实现单层神经网络，并在Iris数据集上进行模型训练。
代码如下：

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from sklearn import datasets

iris=datasets.load_iris()
x_vals=np.array([x[0:3] for x in iris.data])
y_vals=np.array([x[3] for x in iris.data])
sess=tf.Session()

tf.set_random_seed(2)
np.random.seed(2)

train_indices=np.random.choice(len(x_vals),round(len(x_vals)*0.8),replace=False)
test_indices=np.array(list(set(range(len(x_vals)))-set(train_indices)))

x_vals_train=x_vals[train_indices]
x_vals_test=x_vals[test_indices]
y_vals_train=y_vals[train_indices]
y_vals_test=y_vals[test_indices]

def normalize_cols(m):
    col_max=m.max(axis=0)
    col_min=m.min(axis=0)
    return (m-col_min)/(col_max-col_min)

x_vals_train=np.nan_to_num(normalize_cols(x_vals_train))
x_vals_test=np.nan_to_num(normalize_cols(x_vals_test))

batch_size=50
x_data=tf.placeholder(shape=[None,3],dtype=tf.float32)
y_target=tf.placeholder(shape=[None,1],dtype=tf.float32)

hidden_layer_nodes=5
a1=tf.Variable(tf.random_normal(shape=[3,hidden_layer_nodes]))
b1=tf.Variable(tf.random_normal(shape=[hidden_layer_nodes]))
a2=tf.Variable(tf.random_normal(shape=[hidden_layer_nodes,1]))
b2=tf.Variable(tf.random_normal(shape=[1]))

hidden_output=tf.sigmoid(tf.add(tf.matmul(x_data,a1),b1))
#final_output=tf.sigmoid(tf.add(tf.matmul(hidden_output,a2),b2))
final_output=tf.add(tf.matmul(hidden_output,a2),b2)

loss=tf.reduce_mean(tf.square(y_target-final_output))

train_step=tf.train.GradientDescentOptimizer(0.01).minimize(loss)
sess.run(tf.initialize_all_variables())

loss_vec=[]
test_loss=[]
for i in range(1000):
    rand_index=np.random.choice(len(x_vals_train),size=batch_size)
    rand_x=x_vals_train[rand_index]
    rand_y=np.transpose([y_vals_train[rand_index]])
    sess.run(train_step,feed_dict={x_data:rand_x,y_target:rand_y})

    temp_loss=sess.run(loss,feed_dict={x_data:rand_x,y_target:rand_y})
    loss_vec.append(np.sqrt(temp_loss))

    test_temp_loss=sess.run(loss,feed_dict={x_data:x_vals_test,y_target:np.transpose([y_vals_test])})
    test_loss.append(np.sqrt(test_temp_loss))

    if (i+1)%50==0:
        print("Generation:"+str(i+1)+".Loss="+str(temp_loss))

plt.plot(loss_vec,'k-',label='train loss')        
plt.plot(test_loss,'r--',label='test loss')
plt.title("loss per Generation")
plt.xlabel('Generation')
plt.ylabel('Loss')
plt.legend(loc='upper right')
plt.show()