Python实现Keras搭建神经网络训练分类模型教程

我就废话不多说了，大家还是直接看代码吧~

注释讲解版：

# Classifier exampleimport numpy as np# for reproducibilitynp.random.seed(1337)# from keras.datasets import mnistfrom keras.utils import np_utilsfrom keras.models import Sequentialfrom keras.layers import Dense, Activationfrom keras.optimizers import RMSprop# 程序中用到的数据是经典的手写体识别mnist数据集# download the mnist to the path if it is the first time to be called# X shape (60,000 28x28), y# (X_train, y_train), (X_test, y_test) = mnist.load_data()# 下载minst.npz：# 链接: https://pan.baidu.com/s/1b2ppKDOdzDJxivgmyOoQsA# 提取码: y5ir# 将下载好的minst.npz放到当前目录下path=’./mnist.npz’f = np.load(path)X_train, y_train = f[’x_train’], f[’y_train’]X_test, y_test = f[’x_test’], f[’y_test’]f.close()# data pre-processing# 数据预处理# normalize# X shape (60,000 28x28)，表示输入数据 X 是个三维的数据# 可以理解为 60000行数据，每一行是一张28 x 28 的灰度图片# X_train.reshape(X_train.shape[0], -1)表示：只保留第一维，其余的纬度，不管多少纬度，重新排列为一维# 参数-1就是不知道行数或者列数多少的情况下使用的参数# 所以先确定除了参数-1之外的其他参数，然后通过(总参数的计算) / (确定除了参数-1之外的其他参数) = 该位置应该是多少的参数# 这里用-1是偷懒的做法,等同于 28*28# reshape后的数据是：共60000行，每一行是784个数据点（feature）# 输入的 x 变成 60,000*784 的数据，然后除以 255 进行标准化# 因为每个像素都是在 0 到 255 之间的，标准化之后就变成了 0 到 1 之间X_train = X_train.reshape(X_train.shape[0], -1) / 255X_test = X_test.reshape(X_test.shape[0], -1) / 255# 分类标签编码# 将y转化为one-hot vectory_train = np_utils.to_categorical(y_train, num_classes = 10)y_test = np_utils.to_categorical(y_test, num_classes = 10)# Another way to build your neural net# 建立神经网络# 应用了2层的神经网络，前一层的激活函数用的是relu，后一层的激活函数用的是softmax#32是输出的维数model = Sequential([ Dense(32, input_dim=784), Activation(’relu’), Dense(10), Activation(’softmax’)])# Another way to define your optimizer# 优化函数# 优化算法用的是RMSproprmsprop = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)# We add metrics to get more results you want to see# 不自己定义，直接用内置的优化器也行，optimizer=’rmsprop’#激活模型：接下来用 model.compile 激励神经网络model.compile( optimizer=rmsprop, loss=’categorical_crossentropy’, metrics=[’accuracy’])print(’Training------------’)# Another way to train the model# 训练模型# 上一个程序是用train_on_batch 一批一批的训练 X_train, Y_train# 默认的返回值是 cost，每100步输出一下结果# 输出的样式与上一个程序的有所不同，感觉用model.fit()更清晰明了# 上一个程序是Python实现Keras搭建神经网络训练回归模型：# https://blog.csdn.net/weixin_45798684/article/details/106503685model.fit(X_train, y_train, nb_epoch=2, batch_size=32)print(’nTesting------------’)# Evaluate the model with the metrics we defined earlier# 测试loss, accuracy = model.evaluate(X_test, y_test)print(’test loss:’, loss)print(’test accuracy:’, accuracy)

运行结果：

Using TensorFlow backend.Training------------Epoch 1/2 32/60000 [..............................] - ETA: 5:03 - loss: 2.4464 - accuracy: 0.0625 864/60000 [..............................] - ETA: 14s - loss: 1.8023 - accuracy: 0.4850 1696/60000 [..............................] - ETA: 9s - loss: 1.5119 - accuracy: 0.6002 2432/60000 [>.............................] - ETA: 7s - loss: 1.3151 - accuracy: 0.6637 3200/60000 [>.............................] - ETA: 6s - loss: 1.1663 - accuracy: 0.7056 3968/60000 [>.............................] - ETA: 5s - loss: 1.0533 - accuracy: 0.7344 4704/60000 [=>............................] - ETA: 5s - loss: 0.9696 - accuracy: 0.7564 5408/60000 [=>............................] - ETA: 5s - loss: 0.9162 - accuracy: 0.7681 6112/60000 [==>...........................] - ETA: 5s - loss: 0.8692 - accuracy: 0.7804 6784/60000 [==>...........................] - ETA: 4s - loss: 0.8225 - accuracy: 0.7933 7424/60000 [==>...........................] - ETA: 4s - loss: 0.7871 - accuracy: 0.8021 8128/60000 [===>..........................] - ETA: 4s - loss: 0.7546 - accuracy: 0.8099 8960/60000 [===>..........................] - ETA: 4s - loss: 0.7196 - accuracy: 0.8183 9568/60000 [===>..........................] - ETA: 4s - loss: 0.6987 - accuracy: 0.823010144/60000 [====>.........................] - ETA: 4s - loss: 0.6812 - accuracy: 0.826210784/60000 [====>.........................] - ETA: 4s - loss: 0.6640 - accuracy: 0.829711456/60000 [====>.........................] - ETA: 4s - loss: 0.6462 - accuracy: 0.832912128/60000 [=====>........................] - ETA: 4s - loss: 0.6297 - accuracy: 0.836612704/60000 [=====>........................] - ETA: 4s - loss: 0.6156 - accuracy: 0.840513408/60000 [=====>........................] - ETA: 3s - loss: 0.6009 - accuracy: 0.843014112/60000 [======>.......................] - ETA: 3s - loss: 0.5888 - accuracy: 0.845714816/60000 [======>.......................] - ETA: 3s - loss: 0.5772 - accuracy: 0.848715488/60000 [======>.......................] - ETA: 3s - loss: 0.5685 - accuracy: 0.850316192/60000 [=======>......................] - ETA: 3s - loss: 0.5576 - accuracy: 0.853416896/60000 [=======>......................] - ETA: 3s - loss: 0.5477 - accuracy: 0.855517600/60000 [=======>......................] - ETA: 3s - loss: 0.5380 - accuracy: 0.857618240/60000 [========>.....................] - ETA: 3s - loss: 0.5279 - accuracy: 0.860018976/60000 [========>.....................] - ETA: 3s - loss: 0.5208 - accuracy: 0.861719712/60000 [========>.....................] - ETA: 3s - loss: 0.5125 - accuracy: 0.863420416/60000 [=========>....................] - ETA: 3s - loss: 0.5046 - accuracy: 0.865421088/60000 [=========>....................] - ETA: 3s - loss: 0.4992 - accuracy: 0.866921792/60000 [=========>....................] - ETA: 3s - loss: 0.4932 - accuracy: 0.868422432/60000 [==========>...................] - ETA: 3s - loss: 0.4893 - accuracy: 0.869323072/60000 [==========>...................] - ETA: 2s - loss: 0.4845 - accuracy: 0.870323648/60000 [==========>...................] - ETA: 2s - loss: 0.4800 - accuracy: 0.871224096/60000 [===========>..................] - ETA: 2s - loss: 0.4776 - accuracy: 0.871824576/60000 [===========>..................] - ETA: 2s - loss: 0.4733 - accuracy: 0.872825056/60000 [===========>..................] - ETA: 2s - loss: 0.4696 - accuracy: 0.873625568/60000 [===========>..................] - ETA: 2s - loss: 0.4658 - accuracy: 0.874526080/60000 [============>.................] - ETA: 2s - loss: 0.4623 - accuracy: 0.875326592/60000 [============>.................] - ETA: 2s - loss: 0.4600 - accuracy: 0.875627072/60000 [============>.................] - ETA: 2s - loss: 0.4566 - accuracy: 0.876327584/60000 [============>.................] - ETA: 2s - loss: 0.4532 - accuracy: 0.877128032/60000 [=============>................] - ETA: 2s - loss: 0.4513 - accuracy: 0.877528512/60000 [=============>................] - ETA: 2s - loss: 0.4477 - accuracy: 0.878428992/60000 [=============>................] - ETA: 2s - loss: 0.4464 - accuracy: 0.878629472/60000 [=============>................] - ETA: 2s - loss: 0.4439 - accuracy: 0.879129952/60000 [=============>................] - ETA: 2s - loss: 0.4404 - accuracy: 0.880030464/60000 [==============>...............] - ETA: 2s - loss: 0.4375 - accuracy: 0.880730784/60000 [==============>...............] - ETA: 2s - loss: 0.4349 - accuracy: 0.881331296/60000 [==============>...............] - ETA: 2s - loss: 0.4321 - accuracy: 0.882031808/60000 [==============>...............] - ETA: 2s - loss: 0.4301 - accuracy: 0.882732256/60000 [===============>..............] - ETA: 2s - loss: 0.4279 - accuracy: 0.883232736/60000 [===============>..............] - ETA: 2s - loss: 0.4258 - accuracy: 0.883833280/60000 [===============>..............] - ETA: 2s - loss: 0.4228 - accuracy: 0.884433920/60000 [===============>..............] - ETA: 2s - loss: 0.4195 - accuracy: 0.884934560/60000 [================>.............] - ETA: 2s - loss: 0.4179 - accuracy: 0.885235104/60000 [================>.............] - ETA: 2s - loss: 0.4165 - accuracy: 0.885435680/60000 [================>.............] - ETA: 2s - loss: 0.4139 - accuracy: 0.886036288/60000 [=================>............] - ETA: 2s - loss: 0.4111 - accuracy: 0.887036928/60000 [=================>............] - ETA: 2s - loss: 0.4088 - accuracy: 0.887437504/60000 [=================>............] - ETA: 2s - loss: 0.4070 - accuracy: 0.887838048/60000 [==================>...........] - ETA: 1s - loss: 0.4052 - accuracy: 0.888238656/60000 [==================>...........] - ETA: 1s - loss: 0.4031 - accuracy: 0.888839264/60000 [==================>...........] - ETA: 1s - loss: 0.4007 - accuracy: 0.889439840/60000 [==================>...........] - ETA: 1s - loss: 0.3997 - accuracy: 0.889640416/60000 [===================>..........] - ETA: 1s - loss: 0.3978 - accuracy: 0.890140960/60000 [===================>..........] - ETA: 1s - loss: 0.3958 - accuracy: 0.890641504/60000 [===================>..........] - ETA: 1s - loss: 0.3942 - accuracy: 0.891142016/60000 [====================>.........] - ETA: 1s - loss: 0.3928 - accuracy: 0.891542592/60000 [====================>.........] - ETA: 1s - loss: 0.3908 - accuracy: 0.892043168/60000 [====================>.........] - ETA: 1s - loss: 0.3889 - accuracy: 0.892443744/60000 [====================>.........] - ETA: 1s - loss: 0.3868 - accuracy: 0.893144288/60000 [=====================>........] - ETA: 1s - loss: 0.3864 - accuracy: 0.893144832/60000 [=====================>........] - ETA: 1s - loss: 0.3842 - accuracy: 0.893845408/60000 [=====================>........] - ETA: 1s - loss: 0.3822 - accuracy: 0.894445984/60000 [=====================>........] - ETA: 1s - loss: 0.3804 - accuracy: 0.894946560/60000 [======================>.......] - ETA: 1s - loss: 0.3786 - accuracy: 0.895347168/60000 [======================>.......] - ETA: 1s - loss: 0.3767 - accuracy: 0.895847808/60000 [======================>.......] - ETA: 1s - loss: 0.3744 - accuracy: 0.896348416/60000 [=======================>......] - ETA: 1s - loss: 0.3732 - accuracy: 0.896648928/60000 [=======================>......] - ETA: 0s - loss: 0.3714 - accuracy: 0.897149440/60000 [=======================>......] - ETA: 0s - loss: 0.3701 - accuracy: 0.897450048/60000 [========================>.....] - ETA: 0s - loss: 0.3678 - accuracy: 0.897950688/60000 [========================>.....] - ETA: 0s - loss: 0.3669 - accuracy: 0.898351264/60000 [========================>.....] - ETA: 0s - loss: 0.3654 - accuracy: 0.898851872/60000 [========================>.....] - ETA: 0s - loss: 0.3636 - accuracy: 0.899252608/60000 [=========================>....] - ETA: 0s - loss: 0.3618 - accuracy: 0.899753376/60000 [=========================>....] - ETA: 0s - loss: 0.3599 - accuracy: 0.900354048/60000 [==========================>...] - ETA: 0s - loss: 0.3583 - accuracy: 0.900654560/60000 [==========================>...] - ETA: 0s - loss: 0.3568 - accuracy: 0.901055296/60000 [==========================>...] - ETA: 0s - loss: 0.3548 - accuracy: 0.901656064/60000 [===========================>..] - ETA: 0s - loss: 0.3526 - accuracy: 0.902156736/60000 [===========================>..] - ETA: 0s - loss: 0.3514 - accuracy: 0.902657376/60000 [===========================>..] - ETA: 0s - loss: 0.3499 - accuracy: 0.902958112/60000 [============================>.] - ETA: 0s - loss: 0.3482 - accuracy: 0.903358880/60000 [============================>.] - ETA: 0s - loss: 0.3459 - accuracy: 0.903959584/60000 [============================>.] - ETA: 0s - loss: 0.3444 - accuracy: 0.904360000/60000 [==============================] - 5s 87us/step - loss: 0.3435 - accuracy: 0.9046Epoch 2/2 32/60000 [..............................] - ETA: 11s - loss: 0.0655 - accuracy: 1.0000 736/60000 [..............................] - ETA: 4s - loss: 0.2135 - accuracy: 0.9389 1408/60000 [..............................] - ETA: 4s - loss: 0.2217 - accuracy: 0.9361 1984/60000 [..............................] - ETA: 4s - loss: 0.2316 - accuracy: 0.9390 2432/60000 [>.............................] - ETA: 4s - loss: 0.2280 - accuracy: 0.9379 3040/60000 [>.............................] - ETA: 4s - loss: 0.2374 - accuracy: 0.9368 3808/60000 [>.............................] - ETA: 4s - loss: 0.2251 - accuracy: 0.9386 4576/60000 [=>............................] - ETA: 4s - loss: 0.2225 - accuracy: 0.9379 5216/60000 [=>............................] - ETA: 4s - loss: 0.2208 - accuracy: 0.9377 5920/60000 [=>............................] - ETA: 4s - loss: 0.2173 - accuracy: 0.9383 6656/60000 [==>...........................] - ETA: 4s - loss: 0.2217 - accuracy: 0.9370 7392/60000 [==>...........................] - ETA: 4s - loss: 0.2224 - accuracy: 0.9360 8096/60000 [===>..........................] - ETA: 4s - loss: 0.2234 - accuracy: 0.9363 8800/60000 [===>..........................] - ETA: 3s - loss: 0.2235 - accuracy: 0.9358 9408/60000 [===>..........................] - ETA: 3s - loss: 0.2196 - accuracy: 0.936510016/60000 [====>.........................] - ETA: 3s - loss: 0.2207 - accuracy: 0.936310592/60000 [====>.........................] - ETA: 3s - loss: 0.2183 - accuracy: 0.936911168/60000 [====>.........................] - ETA: 3s - loss: 0.2177 - accuracy: 0.937711776/60000 [====>.........................] - ETA: 3s - loss: 0.2154 - accuracy: 0.938512544/60000 [=====>........................] - ETA: 3s - loss: 0.2152 - accuracy: 0.939313216/60000 [=====>........................] - ETA: 3s - loss: 0.2163 - accuracy: 0.939013920/60000 [=====>........................] - ETA: 3s - loss: 0.2155 - accuracy: 0.939114624/60000 [======>.......................] - ETA: 3s - loss: 0.2150 - accuracy: 0.939115424/60000 [======>.......................] - ETA: 3s - loss: 0.2143 - accuracy: 0.939816032/60000 [=======>......................] - ETA: 3s - loss: 0.2122 - accuracy: 0.940516672/60000 [=======>......................] - ETA: 3s - loss: 0.2096 - accuracy: 0.940917344/60000 [=======>......................] - ETA: 3s - loss: 0.2091 - accuracy: 0.941118112/60000 [========>.....................] - ETA: 3s - loss: 0.2086 - accuracy: 0.941618784/60000 [========>.....................] - ETA: 3s - loss: 0.2084 - accuracy: 0.941819392/60000 [========>.....................] - ETA: 3s - loss: 0.2076 - accuracy: 0.941820000/60000 [=========>....................] - ETA: 3s - loss: 0.2067 - accuracy: 0.942120608/60000 [=========>....................] - ETA: 3s - loss: 0.2071 - accuracy: 0.941921184/60000 [=========>....................] - ETA: 3s - loss: 0.2056 - accuracy: 0.942321856/60000 [=========>....................] - ETA: 3s - loss: 0.2063 - accuracy: 0.941922624/60000 [==========>...................] - ETA: 2s - loss: 0.2059 - accuracy: 0.942123328/60000 [==========>...................] - ETA: 2s - loss: 0.2056 - accuracy: 0.942223936/60000 [==========>...................] - ETA: 2s - loss: 0.2051 - accuracy: 0.942324512/60000 [===========>..................] - ETA: 2s - loss: 0.2041 - accuracy: 0.942425248/60000 [===========>..................] - ETA: 2s - loss: 0.2036 - accuracy: 0.942626016/60000 [============>.................] - ETA: 2s - loss: 0.2031 - accuracy: 0.942426656/60000 [============>.................] - ETA: 2s - loss: 0.2035 - accuracy: 0.942227360/60000 [============>.................] - ETA: 2s - loss: 0.2050 - accuracy: 0.941728128/60000 [=============>................] - ETA: 2s - loss: 0.2045 - accuracy: 0.941828896/60000 [=============>................] - ETA: 2s - loss: 0.2046 - accuracy: 0.941829536/60000 [=============>................] - ETA: 2s - loss: 0.2052 - accuracy: 0.941730208/60000 [==============>...............] - ETA: 2s - loss: 0.2050 - accuracy: 0.941730848/60000 [==============>...............] - ETA: 2s - loss: 0.2046 - accuracy: 0.941931552/60000 [==============>...............] - ETA: 2s - loss: 0.2037 - accuracy: 0.942132224/60000 [===============>..............] - ETA: 2s - loss: 0.2043 - accuracy: 0.942032928/60000 [===============>..............] - ETA: 2s - loss: 0.2041 - accuracy: 0.942033632/60000 [===============>..............] - ETA: 2s - loss: 0.2035 - accuracy: 0.942234272/60000 [================>.............] - ETA: 1s - loss: 0.2029 - accuracy: 0.942334944/60000 [================>.............] - ETA: 1s - loss: 0.2030 - accuracy: 0.942335648/60000 [================>.............] - ETA: 1s - loss: 0.2027 - accuracy: 0.942236384/60000 [=================>............] - ETA: 1s - loss: 0.2027 - accuracy: 0.942137120/60000 [=================>............] - ETA: 1s - loss: 0.2024 - accuracy: 0.942137760/60000 [=================>............] - ETA: 1s - loss: 0.2013 - accuracy: 0.942438464/60000 [==================>...........] - ETA: 1s - loss: 0.2011 - accuracy: 0.942439200/60000 [==================>...........] - ETA: 1s - loss: 0.2000 - accuracy: 0.942640000/60000 [===================>..........] - ETA: 1s - loss: 0.1990 - accuracy: 0.942840672/60000 [===================>..........] - ETA: 1s - loss: 0.1986 - accuracy: 0.943041344/60000 [===================>..........] - ETA: 1s - loss: 0.1982 - accuracy: 0.943242112/60000 [====================>.........] - ETA: 1s - loss: 0.1981 - accuracy: 0.943242848/60000 [====================>.........] - ETA: 1s - loss: 0.1977 - accuracy: 0.943343552/60000 [====================>.........] - ETA: 1s - loss: 0.1970 - accuracy: 0.943544256/60000 [=====================>........] - ETA: 1s - loss: 0.1972 - accuracy: 0.943644992/60000 [=====================>........] - ETA: 1s - loss: 0.1972 - accuracy: 0.943745664/60000 [=====================>........] - ETA: 1s - loss: 0.1966 - accuracy: 0.943846176/60000 [======================>.......] - ETA: 1s - loss: 0.1968 - accuracy: 0.943746752/60000 [======================>.......] - ETA: 1s - loss: 0.1969 - accuracy: 0.943847488/60000 [======================>.......] - ETA: 0s - loss: 0.1965 - accuracy: 0.943948256/60000 [=======================>......] - ETA: 0s - loss: 0.1965 - accuracy: 0.943848896/60000 [=======================>......] - ETA: 0s - loss: 0.1963 - accuracy: 0.943649568/60000 [=======================>......] - ETA: 0s - loss: 0.1962 - accuracy: 0.943850304/60000 [========================>.....] - ETA: 0s - loss: 0.1965 - accuracy: 0.943751072/60000 [========================>.....] - ETA: 0s - loss: 0.1967 - accuracy: 0.943751744/60000 [========================>.....] - ETA: 0s - loss: 0.1961 - accuracy: 0.943952480/60000 [=========================>....] - ETA: 0s - loss: 0.1957 - accuracy: 0.943953248/60000 [=========================>....] - ETA: 0s - loss: 0.1959 - accuracy: 0.943854016/60000 [==========================>...] - ETA: 0s - loss: 0.1963 - accuracy: 0.943754592/60000 [==========================>...] - ETA: 0s - loss: 0.1965 - accuracy: 0.943655168/60000 [==========================>...] - ETA: 0s - loss: 0.1962 - accuracy: 0.943655776/60000 [==========================>...] - ETA: 0s - loss: 0.1959 - accuracy: 0.943756448/60000 [===========================>..] - ETA: 0s - loss: 0.1965 - accuracy: 0.943757152/60000 [===========================>..] - ETA: 0s - loss: 0.1958 - accuracy: 0.943957824/60000 [===========================>..] - ETA: 0s - loss: 0.1956 - accuracy: 0.943858560/60000 [============================>.] - ETA: 0s - loss: 0.1951 - accuracy: 0.944059360/60000 [============================>.] - ETA: 0s - loss: 0.1947 - accuracy: 0.944060000/60000 [==============================] - 5s 76us/step - loss: 0.1946 - accuracy: 0.9440Testing------------ 32/10000 [..............................] - ETA: 15s 1248/10000 [==>...........................] - ETA: 0s 2656/10000 [======>.......................] - ETA: 0s 4064/10000 [===========>..................] - ETA: 0s 5216/10000 [==============>...............] - ETA: 0s 6464/10000 [==================>...........] - ETA: 0s 7744/10000 [======================>.......] - ETA: 0s 9056/10000 [==========================>...] - ETA: 0s 9984/10000 [============================>.] - ETA: 0s10000/10000 [==============================] - 0s 47us/steptest loss: 0.17407772153392434test accuracy: 0.9513000249862671

补充知识：Keras 搭建简单神经网络：顺序模型+回归问题

多层全连接神经网络

每层神经元个数、神经网络层数、激活函数等可自由修改

使用不同的损失函数可适用于其他任务，比如：分类问题

这是Keras搭建神经网络模型最基础的方法之一，Keras还有其他进阶的方法，官网给出了一些基本使用方法：Keras官网

# 这里搭建了一个4层全连接神经网络（不算输入层），传入函数以及函数内部的参数均可自由修改def ann(X, y): ’’’ X: 输入的训练集数据 y: 训练集对应的标签 ’’’ ’’’初始化模型’’’ # 首先定义了一个顺序模型作为框架，然后往这个框架里面添加网络层 # 这是最基础搭建神经网络的方法之一 model = Sequential() ’’’开始添加网络层’’’ # Dense表示全连接层，第一层需要我们提供输入的维度 input_shape # Activation表示每层的激活函数，可以传入预定义的激活函数，也可以传入符合接口规则的其他高级激活函数 model.add(Dense(64, input_shape=(X.shape[1],))) model.add(Activation(’sigmoid’)) model.add(Dense(256)) model.add(Activation(’relu’)) model.add(Dense(256)) model.add(Activation(’tanh’)) model.add(Dense(32)) model.add(Activation(’tanh’)) # 输出层，输出的维度大小由具体任务而定 # 这里是一维输出的回归问题 model.add(Dense(1)) model.add(Activation(’linear’)) ’’’模型编译’’’ # optimizer表示优化器（可自由选择），loss表示使用哪一种 model.compile(optimizer=’rmsprop’, loss=’mean_squared_error’) # 自定义学习率，也可以使用原始的基础学习率 reduce_lr = ReduceLROnPlateau(monitor=’loss’, factor=0.1, patience=10, verbose=0, mode=’auto’, min_delta=0.001, cooldown=0, min_lr=0) ’’’模型训练’’’ # 这里的模型也可以先从函数返回后，再进行训练 # epochs表示训练的轮数，batch_size表示每次训练的样本数量（小批量学习），validation_split表示用作验证集的训练数据的比例 # callbacks表示回调函数的集合，用于模型训练时查看模型的内在状态和统计数据，相应的回调函数方法会在各自的阶段被调用 # verbose表示输出的详细程度，值越大输出越详细 model.fit(X, y, epochs=100, batch_size=50, validation_split=0.0, callbacks=[reduce_lr], verbose=0) # 打印模型结构 print(model.summary()) return model

下图是此模型的结构图，其中下划线后面的数字是根据调用次数而定

以上这篇Python实现Keras搭建神经网络训练分类模型教程就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持好吧啦网。