0.整体概述:
1.读入数据集,并使得数据集乱序:
输出data,查看,发现x是120行4列,即有120个数据,每个数据有4个特征,y是每个特征对应的结果:
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target
print(x_data)
print(y_data)
相同的种子使得打乱顺序之后的不同数据集中的数据的相对位置不变:
数据集划分为训练集和测试集:
输入特征和标签进行打包:
基本的神经网络的结构:
迭代计算的过程:
显示:
代码简化一下:
# 包
import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
import numpy as np
# 数据集
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target
# 随机打乱
np.random.seed(116)
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)
# 分成测试集和训练集
x_train = x_data[:-30]
x_test = x_data[-30:]
y_train = y_data[:-30]
y_test = y_data[-30:]
# 数据类型转化
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
# batch
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)
# 随机初始化参数
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))
# 一些变量:
lr = 0.1 # 学习率为0.1
epoch = 500
for epoch in range(epoch) :
# 训练
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_))
grads = tape.gradient(loss, [w1, b1])
w1.assign_sub(lr * grads[0])
b1.assign_sub(lr * grads[1])
# 测试
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
print(acc)