SoftmaxRegression可以说是LogisticRegression的扩展情况,可以实现多分类。
Softmax函数生成每个类别的后验概率,取最大的作为最终类别。
屏蔽tensorflow的警告
import warnings
warnings.filterwarnings('ignore')
import tensorflow as tf
import matplotlib.pyplot as plt
from matplotlib import animation, rc
from IPython.display import HTML
import matplotlib.cm as cm
import numpy as np
tf.enable_eager_execution()
'''生成数据集'''
dot_num = 100
# 服从N(3, 6, 1, 1, 0).的高斯分布中采样
x_p = np.random.normal(3., 1, dot_num)
y_p = np.random.normal(6., 1, dot_num)
y = np.ones(dot_num)
C1 = np.array([x_p, y_p, y]).T
# 服从N(6, 3, 1, 1, 0).的高斯分布中采样
x_n = np.random.normal(6., 1, dot_num)
y_n = np.random.normal(3., 1, dot_num)
y = np.zeros(dot_num)
C2 = np.array([x_n, y_n, y]).T
# 服从N(7, 7, 1, 1, 0).的高斯分布中采样
x_b = np.random.normal(7., 1, dot_num)
y_b = np.random.normal(7., 1, dot_num)
y = np.ones(dot_num)*2
C3 = np.array([x_b, y_b, y]).T
plt.scatter(C1[:, 0], C1[:, 1], c='b', marker='+')
plt.scatter(C2[:, 0], C2[:, 1], c='g', marker='o')
plt.scatter(C3[:, 0], C3[:, 1], c='r', marker='*')
data_set = np.concatenate((C1, C2, C3), axis=0)
np.random.shuffle(data_set)
定义SoftmaxRegression
'''建立模型'''
epsilon = 1e-12
class SoftmaxRegression():
def __init__(self):
'''==============构建模型所需的参数==============='''
self.W = tf.Variable(initial_value=tf.random.uniform(shape=[2,3], minval=-0.1, maxval=0.1),
dtype=tf.float32)
self.b = tf.Variable(initial_value=tf.zeros(shape=[1]), dtype=tf.float32)
self.trainable_variables = [self.W, self.b]
def __call__(self, inp):
inp = np.array(inp, dtype='float32')
logits = tf.matmul(inp, self.W) + self.b # shape(N, 3)
pred = tf.nn.softmax(logits)
return pred
计算损失:y是实际值,ˆy是预测值
def compute_loss(pred, label):
# tf.cast(data,目标数据类型)数据类型转换
# tf.one_hot()独热编码,在有监督学习中对数据集进行标注.例如[1,0,0],[0,1,0]
label = tf.one_hot(tf.cast(label, dtype=tf.int32), dtype=tf.float32, depth=3)
'''
==============实现softmax的交叉熵损失函数===============
# 输入label shape(N, 3), pred shape(N, 3)
# 输出 losses shape(N,) 每一个样本一个loss
'''
losses = -tf.reduce_sum(label * tf.math.log(pred),axis=1)
loss = tf.reduce_mean(losses)
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(label, axis=1), tf.argmax(pred, axis=1)), dtype=tf.float32))
return loss, accuracy
更新梯度:tf.GradientTape()
def train_one_step(model, optimizer, x, y):
with tf.GradientTape() as tape:
pred = model(x)
loss, accuracy = compute_loss(pred, y)
grads = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(grads, model.trainable_variables))
return loss, accuracy
```python
model = SoftmaxRegression()
opt = tf.keras.optimizers.SGD(learning_rate=0.01)
x1, x2, y = list(zip(*data_set))
x = list(zip(x1, x2))
for i in range(1000):
loss, accuracy = train_one_step(model, opt, x, y)
if i%50==49:
print(f'loss: {loss.numpy():.4}\t accuracy: {accuracy.numpy():.4}')
结果展示
plt.scatter(C1[:, 0], C1[:, 1], c='b', marker='+')
plt.scatter(C2[:, 0], C2[:, 1], c='g', marker='o')
plt.scatter(C3[:, 0], C3[:, 1], c='r', marker='*')
x = np.arange(0., 10., 0.1)
y = np.arange(0., 10., 0.1)
X, Y = np.meshgrid(x, y) # 生成网格点坐标矩阵
inp = np.array(list(zip(X.reshape(-1), Y.reshape(-1))), dtype=np.float32)
print(inp.shape)
Z = model(inp) # shape(N,3)
Z = np.argmax(Z, axis=1) # 获取每一行最大值的索引
Z = Z.reshape(X.shape)
plt.contour(X,Y,Z) # 绘制轮廓
plt.show()
loss: 0.7446 accuracy: 0.8
loss: 0.6302 accuracy: 0.85
loss: 0.5656 accuracy: 0.86
loss: 0.5232 accuracy: 0.8633
loss: 0.4929 accuracy: 0.8667
loss: 0.4699 accuracy: 0.87
loss: 0.4519 accuracy: 0.8667
loss: 0.4372 accuracy: 0.8733
loss: 0.4251 accuracy: 0.8733
loss: 0.4149 accuracy: 0.88
loss: 0.4062 accuracy: 0.88
loss: 0.3986 accuracy: 0.88
loss: 0.392 accuracy: 0.88
loss: 0.3862 accuracy: 0.88
loss: 0.3811 accuracy: 0.88
loss: 0.3765 accuracy: 0.88
loss: 0.3723 accuracy: 0.88
loss: 0.3686 accuracy: 0.88
loss: 0.3652 accuracy: 0.88
loss: 0.3621 accuracy: 0.88
(10000, 2)