【小白學習keras教程】一、基于波士頓住房數據集訓練簡單的MLP回歸模型

@Author：Runsen

多層感知機（MLP）有著非常悠久的歷史，多層感知機(MLP)是深度神經網絡(DNN)的基礎算法

MLP基礎知識

目的：創建用于簡單回歸/分類任務的常規神經網絡（即多層感知器）和Keras

MLP結構

每個MLP模型由一個輸入層、幾個隱藏層和一個輸出層組成

每層神經元的數目不受限制

回歸任務的MLP

當目標（y）連續時

對于損失函數和評估指標，通常使用均方誤差（MSE）

from tensorflow.keras.datasets import boston_housing (X_train, y_train), (X_test, y_test) = boston_housing.load_data()

數據集描述

波士頓住房數據集共有506個數據實例（404個培訓和102個測試）

13個屬性（特征）預測“某一地點房屋的中值”

文件編號：https://keras.io/datasets/

1.創建模型

Keras模型對象可以用Sequential類創建

一開始，模型本身是空的。它是通過添加附加層和編譯來完成的

文檔：https://keras.io/models/sequential/

from tensorflow.keras.models import Sequential model = Sequential()

1-1.添加層

Keras層可以添加到模型中

添加層就像一個接一個地堆疊樂高積木

文檔：https://keras.io/layers/core/

from tensorflow.keras.layers import Activation, Dense # Keras model with two hidden layer with 10 neurons each model.add(Dense(10, input_shape = (13,))) # Input layer => input_shape should be explicitly designated model.add(Activation('sigmoid')) model.add(Dense(10)) # Hidden layer => only output dimension should be designated model.add(Activation('sigmoid')) model.add(Dense(10)) # Hidden layer => only output dimension should be designated model.add(Activation('sigmoid')) model.add(Dense(1)) # Output layer => output dimension = 1 since it is regression problem # This is equivalent to the above code block model.add(Dense(10, input_shape = (13,), activation = 'sigmoid')) model.add(Dense(10, activation = 'sigmoid')) model.add(Dense(10, activation = 'sigmoid')) model.add(Dense(1))

1-2.模型編譯

Keras模型應在培訓前“編譯”

應指定損失類型（函數）和優化器

文檔（優化器）：https://keras.io/optimizers/

文檔（損失）：https://keras.io/losses/

from tensorflow.keras import optimizers sgd = optimizers.SGD(lr = 0.01) # stochastic gradient descent optimizer model.compile(optimizer = sgd, loss = 'mean_squared_error', metrics = ['mse']) # for regression problems, mean squared error (MSE) is often employed

模型摘要

model.summary()

odel: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= dense (Dense) (None, 10) 140 _________________________________________________________________ activation (Activation) (None, 10) 0 _________________________________________________________________ dense_1 (Dense) (None, 10) 110 _________________________________________________________________ activation_1 (Activation) (None, 10) 0 _________________________________________________________________ dense_2 (Dense) (None, 10) 110 _________________________________________________________________ activation_2 (Activation) (None, 10) 0 _________________________________________________________________ dense_3 (Dense) (None, 1) 11 _________________________________________________________________ dense_4 (Dense) (None, 10) 20 _________________________________________________________________ dense_5 (Dense) (None, 10) 110 _________________________________________________________________ dense_6 (Dense) (None, 10) 110 _________________________________________________________________ dense_7 (Dense) (None, 1) 11 ================================================================= Total params: 622 Trainable params: 622 Non-trainable params: 0 _________________________________________________________________

2.培訓

使用提供的訓練數據訓練模型

model.fit(X_train, y_train, batch_size = 50, epochs = 100, verbose = 1)

3.評估

Keras模型可以用evaluate（）函數計算

評估結果包含在列表中

文檔：https://keras.io/metrics/

results = model.evaluate(X_test, y_test)

print(model.metrics_names) # list of metric names the model is employing print(results) # actual figure of metrics computed

print('loss: ', results[0]) print('mse: ', results[1])

Keras 機器學習

版權聲明：本文內容由網絡用戶投稿，版權歸原作者所有，本站不擁有其著作權，亦不承擔相應法律責任。如果您發現本站中有涉嫌抄襲或描述失實的內容，請聯系我們jiasou666@gmail.com 處理，核實后本網站將在24小時內刪除侵權內容。