import tensorflow as tf
from tensorflow import keras
import numpy as np
from sklearn.datasets import make_classification
import matplotlib.pyplot as plt
print(f'Tensorflow version = {tf.__version__}')
print(f'Keras version = {keras.__version__}')
Tensor张量：多维数组，表示视觉数据（输入/输出）
分类实验：
np.random.seed(0) # pick the seed for reproducibility - change it to explore the effects of random variations
n = 100X, Y = make_classification(n_samples = n, n_features=2, n_redundant=0, n_informative=2, flip_y=0.05,class_sep=1.5)
X = X.astype(np.float32)
Y = Y.astype(np.int32)
split = [ 70*n//100 ]
train_x, test_x = np.split(X, split)
train_labels, test_labels = np.split(Y, split)
def plot_dataset(features, labels, W=None, b=None):
# prepare the plot
fig, ax = plt.subplots(1, 1)
ax.set_xlabel('$x_i[0]$ -- (feature 1)')
ax.set_ylabel('$x_i[1]$ -- (feature 2)')
colors = ['r' if l else 'b' for l in labels]
ax.scatter(features[:, 0], features[:, 1], marker='o', c=colors, s=100, alpha = 0.5)
if W is not None:
min_x = min(features[:,0])
max_x = max(features[:,1])
min_y = min(features[:,1])*(1-.1)
max_y = max(features[:,1])*(1+.1)
cx = np.array([min_x,max_x],dtype=np.float32)
cy = (0.5-W[0]*cx-b)/W[1]
ax.plot(cx,cy,'g')
ax.set_ylim(min_y,max_y)
fig.show()
绘图：
plot_dataset(train_x, train_labels)
数据规格化：
train_x_norm = (train_x-np.min(train_x,axis=0)) / (np.max(train_x,axis=0)-np.min(train_x,axis=0))test_x_norm = (test_x-np.min(train_x,axis=0)) / (np.max(train_x,axis=0)-np.min(train_x,axis=0))
训练单层神经/感知器：
一个神经网络=一串层次，在Keras用Sequential模型定义
model = keras.models.Sequential()
model.add(keras.Input(shape=(2,)))
model.add(keras.layers.Dense(1))
model.add(keras.layers.Activation(keras.activations.sigmoid))
model.summary()
输出：
输入层（严格来说不是层）：定义网络输入大小
压缩层：含有w的真实传感器
激活函数层：展示结果0-1
model = keras.models.Sequential()
model.add(keras.layers.Dense(1,input_shape=(2,),activation='sigmoid'))
model.summary()
model.compile(optimizer=keras.optimizers.SGD(learning_rate=0.2),loss='binary_crossentropy',metrics=['acc'])
model.fit(x=train_x_norm,y=train_labels,validation_data=(test_x_norm,test_labels),epochs=10,batch_size=1)
运行过程：
输出：
<keras.callbacks.History at 0x2c420b89910>
绘图：
plot_dataset(train_x,train_labels,model.layers[0].weights[0],model.layers[0].weights[1])
绘制训练图：
model = keras.models.Sequential([
keras.layers.Dense(1,input_shape=(2,),activation='sigmoid')])
model.compile(optimizer=keras.optimizers.SGD(learning_rate=0.05),loss='binary_crossentropy',metrics=['acc'])
hist = model.fit(x=train_x_norm,y=train_labels,validation_data=(test_x_norm,test_labels),epochs=10,batch_size=1)
过程：
输入：
plt.plot(hist.history['acc'])
plt.plot(hist.history['val_acc'])
输出：
多类分类：
model = keras.models.Sequential([
keras.layers.Dense(5,input_shape=(2,),activation='relu'),
keras.layers.Dense(2,activation='softmax')])model.compile(keras.optimizers.Adam(0.01),'categorical_crossentropy',['acc'])
# Two ways to convert to one-hot encodingtrain_labels_onehot = keras.utils.to_categorical(train_labels)
test_labels_onehot = np.eye(2)[test_labels]
hist = model.fit(x=train_x_norm,y=train_labels_onehot,
validation_data=[test_x_norm,test_labels_onehot],batch_size=1,epochs=10)
过程：
Epoch 1/10
70/70 [==============================] - 1s 6ms/step - loss: 0.6524 - acc: 0.7000 - val_loss: 0.5936 - val_acc: 0.9000
Epoch 2/10
70/70 [==============================] - 0s 2ms/step - loss: 0.5715 - acc: 0.8286 - val_loss: 0.5255 - val_acc: 0.8333
Epoch 3/10
70/70 [==============================] - 0s 3ms/step - loss: 0.4820 - acc: 0.8714 - val_loss: 0.4213 - val_acc: 0.9000
Epoch 4/10
70/70 [==============================] - 0s 3ms/step - loss: 0.4426 - acc: 0.9000 - val_loss: 0.3694 - val_acc: 0.9333
Epoch 5/10
70/70 [==============================] - 0s 3ms/step - loss: 0.3602 - acc: 0.9000 - val_loss: 0.3454 - val_acc: 0.9000
Epoch 6/10
70/70 [==============================] - 0s 3ms/step - loss: 0.3209 - acc: 0.8857 - val_loss: 0.2862 - val_acc: 0.9333
Epoch 7/10
70/70 [==============================] - 0s 3ms/step - loss: 0.2905 - acc: 0.9286 - val_loss: 0.2787 - val_acc: 0.9000
Epoch 8/10
70/70 [==============================] - 0s 3ms/step - loss: 0.2698 - acc: 0.9000 - val_loss: 0.2381 - val_acc: 0.9333
Epoch 9/10
70/70 [==============================] - 0s 3ms/step - loss: 0.2639 - acc: 0.8857 - val_loss: 0.2217 - val_acc: 0.9667
Epoch 10/10
70/70 [==============================] - 0s 2ms/step - loss: 0.2592 - acc: 0.9286 - val_loss: 0.2391 - val_acc: 0.9000
系数分类交叉熵损失：
model.compile(keras.optimizers.Adam(0.01),'sparse_categorical_crossentropy',['acc'])
model.fit(x=train_x_norm,y=train_labels,validation_data=[test_x_norm,test_labels],batch_size=1,epochs=10)
过程：
Epoch 1/10 70/70 [==============================] - 1s 6ms/step - loss: 0.2353 - acc: 0.9143 - val_loss: 0.2190 - val_acc: 0.9000 Epoch 2/10 70/70 [==============================] - 0s 3ms/step - loss: 0.2243 - acc: 0.9286 - val_loss: 0.1886 - val_acc: 0.9333 Epoch 3/10 70/70 [==============================] - 0s 2ms/step - loss: 0.2366 - acc: 0.9143 - val_loss: 0.2262 - val_acc: 0.9000 Epoch 4/10 70/70 [==============================] - 0s 2ms/step - loss: 0.2259 - acc: 0.9429 - val_loss: 0.2124 - val_acc: 0.9000 Epoch 5/10 70/70 [==============================] - 0s 2ms/step - loss: 0.2061 - acc: 0.9429 - val_loss: 0.2691 - val_acc: 0.9000 Epoch 6/10 70/70 [==============================] - 0s 2ms/step - loss: 0.2200 - acc: 0.9286 - val_loss: 0.2344 - val_acc: 0.9000 Epoch 7/10 70/70 [==============================] - 0s 3ms/step - loss: 0.2133 - acc: 0.9286 - val_loss: 0.1973 - val_acc: 0.9000 Epoch 8/10 70/70 [==============================] - 0s 3ms/step - loss: 0.2062 - acc: 0.9429 - val_loss: 0.1893 - val_acc: 0.9000 Epoch 9/10 70/70 [==============================] - 0s 3ms/step - loss: 0.2060 - acc: 0.9571 - val_loss: 0.2719 - val_acc: 0.9000 Epoch 10/10 70/70 [==============================] - 0s 3ms/step - loss: 0.2021 - acc: 0.9571 - val_loss: 0.2293 - val_acc: 0.9000
输出：
<keras.callbacks.History at 0x2c42267de80>
多标签分类： -
总结：
相似文章：
-
Keras在MNIST实验的应用
-
2024/2/3 - 神经网络实验 - Keras+Tensorflow 2.x试水
-
2024/2/3 - 神经网络实验 - PyTorch试水