LSTM CNN-LSTM ConvLSTM for UCI-HAR

LSTM

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import os

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.layers import LSTM
from tensorflow.keras.utils import to_categorical

def load_file(filepath):
    dataframe = pd.read_csv(filepath, header=None, delim_whitespace=True)
    return dataframe.values

def load_dataset(data_rootdir, dirname, group):
    '''
    该函数实现将训练数据或测试数据文件列表堆叠为三维数组
    '''
    filename_list = []
    filepath_list = []
    X = []
    
    # os.walk() 方法是一个简单易用的文件、目录遍历器，可以高效的处理文件、目录。
    for rootdir, dirnames, filenames in os.walk(data_rootdir + dirname):
        for filename in filenames:
            filename_list.append(filename)
            filepath_list.append(os.path.join(rootdir, filename))
        #print(filename_list)
        #print(filepath_list)
    
    # 遍历根目录下的文件，并读取为DataFrame格式；
    for filepath in filepath_list:
        X.append(load_file(filepath))
    
    X = np.dstack(X) # dstack沿第三个维度叠加，两个二维数组叠加后，前两个维度尺寸不变，第三个维度增加；
    y = load_file(data_rootdir+'/y_'+group+'.txt')
    # one-hot编码。这个之前的文章中提到了，因为原数据集标签从1开始，而one-hot编码从0开始，所以要先减去1
    y = to_categorical(y-1)
    print('{}_X.shape:{},{}_y.shape:{}\n'.format(group,X.shape,group,y.shape))
    return X, y


def evaluate_model(trainX, trainy, testX, testy):
    verbose, epochs, batch_size = 0, 15, 64
    n_timesteps, n_features, n_outputs = trainX.shape[1], trainX.shape[2], trainy.shape[1]
    
    model = Sequential()
    model.add(LSTM(100, input_shape=(n_timesteps,n_features)))
    model.add(Dropout(0.5))
    model.add(Dense(100, activation='relu'))
    model.add(Dense(n_outputs, activation='softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    
    model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=verbose)

    _, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
    return accuracy
        

def run_experiment(trainX, trainy, testX, testy, repeats=10):

    scores = list()
    for r in range(repeats):
        score = evaluate_model(trainX, trainy, testX, testy)
        score = score * 100.0
        print('>#%d: %.3f' % (r+1, score))
        scores.append(score)
    
    m, s = np.mean(scores), np.std(scores)
    print('Accuracy: %.3f%% (+/-%.3f)' % (m, s))

if __name__ == '__main__':
    train_dir = 'D:/GraduationCode/01 Datasets/UCI HAR Dataset/train/'
    test_dir = 'D:/GraduationCode/01 Datasets/UCI HAR Dataset/test/'
    dirname = '/Inertial Signals/'
    trainX, trainy = load_dataset(train_dir, dirname, 'train')
    testX, testy = load_dataset(test_dir, dirname, 'test')

    run_experiment(trainX, trainy, testX, testy, repeats=10)

train_X.shape:(7352, 128, 9),train_y.shape:(7352, 6)

test_X.shape:(2947, 128, 9),test_y.shape:(2947, 6)

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_1 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_1 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 100)               10100     
_________________________________________________________________
dense_3 (Dense)              (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#1: 90.770
Model: "sequential_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_2 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_2 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_4 (Dense)              (None, 100)               10100     
_________________________________________________________________
dense_5 (Dense)              (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#2: 90.804
Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_3 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_3 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_6 (Dense)              (None, 100)               10100     
_________________________________________________________________
dense_7 (Dense)              (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#3: 88.768
Model: "sequential_4"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_4 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_4 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_8 (Dense)              (None, 100)               10100     
_________________________________________________________________
dense_9 (Dense)              (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#4: 88.870
Model: "sequential_5"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_5 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_5 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_10 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_11 (Dense)             (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#5: 90.227
Model: "sequential_6"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_6 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_6 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_12 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_13 (Dense)             (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#6: 87.615
Model: "sequential_7"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_7 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_7 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_14 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_15 (Dense)             (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#7: 91.313
Model: "sequential_8"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_8 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_8 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_16 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_17 (Dense)             (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#8: 87.479
Model: "sequential_9"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_9 (LSTM)                (None, 100)               44000     
_________________________________________________________________
dropout_9 (Dropout)          (None, 100)               0         
_________________________________________________________________
dense_18 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_19 (Dense)             (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None

>#9: 91.144
Model: "sequential_10"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_10 (LSTM)               (None, 100)               44000     
_________________________________________________________________
dropout_10 (Dropout)         (None, 100)               0         
_________________________________________________________________
dense_20 (Dense)             (None, 100)               10100     
_________________________________________________________________
dense_21 (Dense)             (None, 6)                 606       
=================================================================
Total params: 54,706
Trainable params: 54,706
Non-trainable params: 0
_________________________________________________________________
None
>#10: 90.092
Accuracy: 89.708% (+/-1.354)

CNN-LSTM

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import os

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv1D, MaxPooling1D
from tensorflow.keras.layers import LSTM, TimeDistributed, ConvLSTM2D
from tensorflow.keras.utils import to_categorical

def load_file(filepath):
    dataframe = pd.read_csv(filepath, header=None, delim_whitespace=True)
    return dataframe.values

def load_dataset(data_rootdir, dirname, group):
    '''
    该函数实现将训练数据或测试数据文件列表堆叠为三维数组
    '''
    filename_list = []
    filepath_list = []
    X = []
    
    # os.walk() 方法是一个简单易用的文件、目录遍历器，可以高效的处理文件、目录。
    for rootdir, dirnames, filenames in os.walk(data_rootdir + dirname):
        for filename in filenames:
            filename_list.append(filename)
            filepath_list.append(os.path.join(rootdir, filename))
        #print(filename_list)
        #print(filepath_list)
    
    # 遍历根目录下的文件，并读取为DataFrame格式；
    for filepath in filepath_list:
        X.append(load_file(filepath))
    
    X = np.dstack(X) # dstack沿第三个维度叠加，两个二维数组叠加后，前两个维度尺寸不变，第三个维度增加；
    y = load_file(data_rootdir+'/y_'+group+'.txt')
    # one-hot编码。这个之前的文章中提到了，因为原数据集标签从1开始，而one-hot编码从0开始，所以要先减去1
    y = to_categorical(y-1)
    print('{}_X.shape:{},{}_y.shape:{}\n'.format(group,X.shape,group,y.shape))
    return X, y


def evaluate_model(trainX, trainy, testX, testy):
    verbose, epochs, batch_size = 0, 25, 64
    n_timesteps, n_features, n_outputs = trainX.shape[1], trainX.shape[2], trainy.shape[1]

    n_steps, n_length = 4, 32
    trainX = trainX.reshape((trainX.shape[0], n_steps, n_length, n_features))
    testX = testX.reshape((testX.shape[0], n_steps, n_length, n_features))

    model = Sequential()
    model.add(TimeDistributed(Conv1D(filters=64, kernel_size=3, activation='relu'), 
                              input_shape=(None, n_length, n_features)))
    model.add(TimeDistributed(Conv1D(filters=64, kernel_size=3, activation='relu')))
    model.add(TimeDistributed(Dropout(0.5)))
    model.add(TimeDistributed(MaxPooling1D(pool_size=2)))
    model.add(TimeDistributed(Flatten()))
    model.add(LSTM(100))
    model.add(Dropout(0.5))
    model.add(Dense(100, activation='relu'))
    model.add(Dense(n_outputs, activation='softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    
    model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=verbose)

    _, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
    return accuracy
        

def run_experiment(trainX, trainy, testX, testy, repeats=10):

    scores = list()
    for r in range(repeats):
        score = evaluate_model(trainX, trainy, testX, testy)
        score = score * 100.0
        print('>#%d: %.3f' % (r+1, score))
        scores.append(score)
    
    m, s = np.mean(scores), np.std(scores)
    print('Accuracy: %.3f%% (+/-%.3f)' % (m, s))

if __name__ == '__main__':
    train_dir = 'D:/GraduationCode/01 Datasets/UCI HAR Dataset/train/'
    test_dir = 'D:/GraduationCode/01 Datasets/UCI HAR Dataset/test/'
    dirname = '/Inertial Signals/'
    trainX, trainy = load_dataset(train_dir, dirname, 'train')
    testX, testy = load_dataset(test_dir, dirname, 'test')

    run_experiment(trainX, trainy, testX, testy, repeats=2)

train_X.shape:(7352, 128, 9),train_y.shape:(7352, 6)

test_X.shape:(2947, 128, 9),test_y.shape:(2947, 6)

>#1: 90.126
>#2: 90.872
Accuracy: 90.499% (+/-0.373)

ConvLSTM

import numpy as np
import matplotlib.pyplot as plt
import os

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.layers import LSTM, TimeDistributed, ConvLSTM2D
from tensorflow.keras.utils import to_categorical

def load_file(filepath):
    dataframe = pd.read_csv(filepath, header=None, delim_whitespace=True)
    return dataframe.values

def load_dataset(data_rootdir, dirname, group):
    '''
    该函数实现将训练数据或测试数据文件列表堆叠为三维数组
    '''
    filename_list = []
    filepath_list = []
    X = []
    
    # os.walk() 方法是一个简单易用的文件、目录遍历器，可以高效的处理文件、目录。
    for rootdir, dirnames, filenames in os.walk(data_rootdir + dirname):
        for filename in filenames:
            filename_list.append(filename)
            filepath_list.append(os.path.join(rootdir, filename))
        #print(filename_list)
        #print(filepath_list)
    
    # 遍历根目录下的文件，并读取为DataFrame格式；
    for filepath in filepath_list:
        X.append(load_file(filepath))
    
    X = np.dstack(X) # dstack沿第三个维度叠加，两个二维数组叠加后，前两个维度尺寸不变，第三个维度增加；
    y = load_file(data_rootdir+'/y_'+group+'.txt')
    # one-hot编码。这个之前的文章中提到了，因为原数据集标签从1开始，而one-hot编码从0开始，所以要先减去1
    y = to_categorical(y-1)
    print('{}_X.shape:{},{}_y.shape:{}\n'.format(group,X.shape,group,y.shape))
    return X, y


def evaluate_model(trainX, trainy, testX, testy):
    verbose, epochs, batch_size = 0, 25, 64
    n_timesteps, n_features, n_outputs = trainX.shape[1], trainX.shape[2], trainy.shape[1]

    n_steps, n_length = 4, 32

    trainX = trainX.reshape((trainX.shape[0], n_steps, 1, n_length, n_features))
    testX = testX.reshape((testX.shape[0], n_steps, 1, n_length, n_features))

    model = Sequential()
    model.add(ConvLSTM2D(filters=64, kernel_size=(1,3), activation='relu', input_shape=(n_steps, 1, n_length, n_features)))
    model.add(Dropout(0.5))
    model.add(Flatten())
    model.add(Dense(100, activation='relu'))
    model.add(Dense(n_outputs, activation='softmax'))
    
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    
    model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=verbose)

    _, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
    return accuracy
        

def run_experiment(trainX, trainy, testX, testy, repeats=10):

    scores = list()
    for r in range(repeats):
        score = evaluate_model(trainX, trainy, testX, testy)
        score = score * 100.0
        print('>#%d: %.3f' % (r+1, score))
        scores.append(score)
    
    m, s = np.mean(scores), np.std(scores)
    print('Accuracy: %.3f%% (+/-%.3f)' % (m, s))

if __name__ == '__main__':
    train_dir = 'D:/GraduationCode/01 Datasets/UCI HAR Dataset/train/'
    test_dir = 'D:/GraduationCode/01 Datasets/UCI HAR Dataset/test/'
    dirname = '/Inertial Signals/'
    trainX, trainy = load_dataset(train_dir, dirname,'train'')
    testX, testy = load_dataset(test_dir, dirname, 'test')

    run_experiment(trainX, trainy, testX, testy, repeats=2)

train_X.shape:(7352, 128, 9),train_y.shape:(7352, 6)

test_X.shape:(2947, 128, 9),test_y.shape:(2947, 6)

>#1: 90.159
>#2: 91.347
Accuracy: 90.753% (+/-0.594)