神经网络----TF1与TF2代码实现鸢尾花分类

运行环境：

python3.6.5+tensorflow1.13.2

python3.7+tensorflow2.0

Tensorflow1：

1.首先加载鸢尾花数据集，读入输入特征以及标签

直接采用load函数加载：

x_data = datasets.load_iris().data  # .data返回iris数据集所有输入特征
y_data = datasets.load_iris().target  # .target返回iris数据集所有标签

2.为保证准确性，对数据集进行打乱

 使用相同的seed，保证输入特征和标签一一对应

np.random.seed(116) 
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)

3. 将打乱后的数据集分割为训练集和测试集，训练集为前120行，测试集为后30行

x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]

4.对x的数据类型进行，否则后面矩阵相乘时会因数据类型不一致报错，利用from_tensor_slices函数使输入特征和标签值一一对应。（把数据集分批次，每个批次batch组数据，这里分为32组）

x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)

train_db = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)

5.定义神经网络可训练参数

w1 = tf.Variable(tf.random.truncated_normal([4, 3], stddev=0.1, seed=1))
b1 = tf.Variable(tf.random.truncated_normal([3], stddev=0.1, seed=1))

6.训练函数

for epoch in range(epoch): 
    for step, (x_train, y_train) in enumerate(train_db): 
        with tf.GradientTape() as tape:  
            y = tf.matmul(x_train, w1) + b1  
            y = tf.nn.softmax(y) 
            y_ = tf.one_hot(y_train, depth=3)  
            loss = tf.reduce_mean(tf.square(y_ - y))  
            loss_all += loss.numpy()  
        grads = tape.gradient(loss, [w1, b1])

        w1.assign_sub(lr * grads[0])
        b1.assign_sub(lr * grads[1]) 

    print("Epoch {}, loss: {}".format(epoch, loss_all/4))
    train_loss_results.append(loss_all / 4) 
    loss_all = 0  

7.测试函数

 total_correct, total_number = 0, 0
    for x_test, y_test in test_db:
        y = tf.matmul(x_test, w1) + b1
        y = tf.nn.softmax(y)
        pred = tf.argmax(y, axis=1)  
        pred = tf.cast(pred, dtype=y_test.dtype)
        correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
        correct = tf.reduce_sum(correct)
        total_correct += int(correct)
        total_number += x_test.shape[0]
    acc = total_correct / total_number
    test_acc.append(acc)
    print("Test_acc:", acc)
    print("--------------------------")

8.运行结果：

准确度曲线： 

损失函数曲线：

 

源码：//download.csdn.net/download/qq_41573860/12377721

 

Tensorflow2

import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

#加载数据集
TRAIN_URL='http://download.tensorflow.org/data/iris_training.csv'
train_path=tf.keras.utils.get_file(TRAIN_URL.split('/')[-1],TRAIN_URL)

TEST_URL='http://download.tensorflow.org/data/iris_test.csv'
test_path=tf.keras.utils.get_file(TEST_URL.split('/')[-1],TEST_URL)

df_iris_train=pd.read_csv(train_path,header=0)
df_iris_test=pd.read_csv(test_path,header=0)

iris_train=np.array(df_iris_train)
iris_test=np.array(df_iris_test)
print(iris_test.shape)
print(iris_train.shape)

#数据处理
x_train=iris_train[:,0:4]
y_train=iris_train[:,4]

x_test=iris_test[:,0:4]
y_test=iris_test[:,4]

x_train=x_train-np.mean(x_train,axis=0)     #对属性值进行标准化处理
x_test=x_test-np.mean(x_test,axis=0)
print(x_train.dtype)
print(y_train.dtype)

X_train=tf.cast(x_train,tf.float32)
Y_train=tf.one_hot(tf.constant(y_train,dtype=tf.int32),3)
print(y_train)
print(Y_train)
X_test=tf.cast(x_test,tf.float32)
Y_test=tf.one_hot(tf.constant(y_test,dtype=tf.int32),3)

print(X_train.shape)
print(Y_train.shape)
print(X_test.shape)
print(Y_test.shape)

#设置超参
learn_rate=0.5
iter=50
display_step=10

#设置模型的参数初始值
np.random.seed(612)
W=tf.Variable(np.random.randn(4,3),dtype=tf.float32)
b=tf.Variable(np.zeros([3]),dtype=tf.float32)

#构建模型
acc_train=[]
acc_test=[]
cce_train=[]
cce_test=[]

for i in range(0,iter+1):
    with tf.GradientTape() as tape:
        pred_train=tf.nn.softmax(tf.matmul(X_train,W)+b)
        print(pred_train)
        loss_train=tf.reduce_mean(tf.keras.losses.categorical_crossentropy(y_true=Y_train,y_pred=pred_train))

    pred_test=tf.nn.softmax(tf.matmul(X_test,W)+b)
    loss_test = tf.reduce_mean(tf.keras.losses.categorical_crossentropy(y_true=Y_test, y_pred=pred_test))

    accuracy_train=tf.reduce_mean(tf.cast(tf.equal(tf.argmax(pred_train.numpy(), axis=1), y_train), tf.float32))
    accuracy_test = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(pred_test.numpy(), axis=1), y_test), tf.float32))

    acc_train.append(accuracy_train)
    acc_test.append(accuracy_test)
    cce_train.append(loss_train)
    cce_test.append(loss_test)

    grads=tape.gradient(loss_train,[W,b])
    W.assign_sub(learn_rate*grads[0])
    b.assign_sub(learn_rate*grads[1])

    if i %display_step == 0:
        print("i:%i,accuracy_train:%f,loss_train:%f,test_acc:%f,test_loss:%f" % (i,accuracy_train,loss_train,accuracy_test,loss_test))