版本python3.7 tensorflow版本為tensorflow-gpu版本2.6
執行結果：
程式碼：
import numpy as np from keras.models import Sequential from keras.layers import Dense, Dropout, Activation, Flatten import matplotlib.pyplot as plt from sklearn import datasets # 樣本資料集，兩個特徵列，兩個分類二分類不需要onehot編碼，直接將類別轉換為0和1，分別代表正樣本的機率。 X,y=datasets.make_classification(n_samples=200, n_features=2, n_informative=2, n_redundant=0,n_repeated=0, n_classes=2, n_clusters_per_class=1) # 構建神經網路模型 model = Sequential() model.add(Dense(input_dim=2, units=1)) model.add(Activation('sigmoid')) # 選定loss函式和最佳化器 model.compile(loss='binary_crossentropy', optimizer='sgd') # 訓練過程 print('Training -----------') for step in range(501): cost = model.train_on_batch(X, y) if step % 50 == 0: print("After %d trainings, the cost: %f" % (step, cost)) # 測試過程 print('\nTesting ------------') cost = model.evaluate(X, y, batch_size=40) print('test cost:', cost) W, b = model.layers[0].get_weights() print('Weights=', W, '\nbiases=', b) # 將訓練結果繪出 Y_pred = model.predict(X) Y_pred = (Y_pred*2).astype('int') # 將機率轉化為類標號，機率在0-0.5時，轉為0，機率在0.5-1時轉為1 # 繪製散點圖 引數：x橫軸 y縱軸 plt.subplot(2,1,1).scatter(X[:,0], X[:,1], c=Y_pred[:,0]) plt.subplot(2,1,2).scatter(X[:,0], X[:,1], c=y) plt.show()