【Machine Learning】17.多分类问题

之前说的都是简单的二分类问题，今天扩展到多分类问题

1.导入

import numpy as np
import matplotlib.pyplot as plt
%matplotlib widget
from sklearn.datasets import make_blobs
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
np.set_printoptions(precision=2)
from lab_utils_multiclass_TF import *
import logging
logging.getLogger("tensorflow").setLevel(logging.ERROR)
tf.autograph.set_verbosity(0)

2.多分类问题

此类网络的最后一层将有多个单元。每个输出都与一个类别相关联。当输入示例应用于网络时，具有最大值的输出是预测的类别。如果输出应用于softmax函数，则softmax的输出将提供输入在每个类别中的概率。

2.1 加载并可视化数据

加载数据

# make 4-class dataset for classification
classes = 4
m = 100
centers = [[-5, 2], [-2, -2], [1, 2], [5, -2]]
std = 1.0
X_train, y_train = make_blobs(n_samples=m, centers=centers, cluster_std=std,random_state=30)

def plt_mc(X_train,y_train,classes, centers, std):
    css = np.unique(y_train)
    fig,ax = plt.subplots(1,1,figsize=(3,3))
    fig.canvas.toolbar_visible = False
    fig.canvas.header_visible = False
    fig.canvas.footer_visible = False
    plt_mc_data(ax, X_train,y_train,classes, map=dkcolors_map, legend=True, size=50, equal_xy = False)
    ax.set_title("Multiclass Data")
    ax.set_xlabel("x0")
    ax.set_ylabel("x1")
    #for c in css:
    #    circ = plt.Circle(centers[c], 2*std, color=dkcolors_map(c), clip_on=False, fill=False, lw=0.5)
    #    ax.add_patch(circ)
    plt.show()

plt_mc(X_train,y_train,classes, centers, std=std)