Python train_model示例

示例#1

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='sony_aibo',
                          epochs=2000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='sony_aibo',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#2

文件： 36-InsectWingbeatSound_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='insect_wingbeat_sound',
                          epochs=1000,
                          batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='insect_wingbeat_sound',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#3

文件： 3-BeetleFly_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='beetle_fly',
                          epochs=8000,
                          batch_size=64)
    summary = model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='beetle_fly',
                                             batch_size=64)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#4

文件： 69-SyntheticControl_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='synthetic_control',
                          epochs=4000,
                          batch_size=16)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='synthetic_control',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#5

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='italy_power_demand',
                          epochs=2000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='italy_power_demand',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#6

文件： 44-MiddlePhalanxOutlineAgeGroup_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='middle_phalanx_age_group',
                          epochs=2000,
                          batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='middle_phalanx_age_group',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#7

文件： 32-HandOutlines_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

        model = generate_GRU_FCN_model()
        start_time = time.time()
    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model() 
        start_time = time.time()

    history = train_model(model, DATASET_INDEX, dataset_prefix='hand_outlines', epochs=2000, batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model, DATASET_INDEX, dataset_prefix='hand_outlines', batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" % ((time.time() - start_time)/60.0))  
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time ="+ str(((time.time() - start_time)))+" seconds ---"
                    +"\n" +"--- Run Time = "+str(((time.time() - start_time)/60.0))+" minutes ---"+"\n")
    print(history.history.keys())
    
    
    plt.plot(history.history['loss'])
    plt.xlabel('epoch', fontsize=16)
    plt.ylabel('loss',fontsize=16)
    plt.savefig("./resulted_plotes/train_loss.jpg")

示例#8

        start_time = time.time()
    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model() 
        start_time = time.time()


    history = train_model(model, DATASET_INDEX, dataset_prefix='coffee', epochs=500, batch_size=64)
    summary = model.summary()

    accuracy, loss, f_score = evaluate_model(model, DATASET_INDEX, dataset_prefix='coffee', batch_size=64)
    
    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" % ((time.time() - start_time)/60.0))  
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time ="+ str(((time.time() - start_time)))+" seconds ---"
                    +"\n" +"--- Run Time = "+str(((time.time() - start_time)/60.0))+" minutes ---"+"\n")

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" % ((time.time() - start_time)/60.0))  
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time ="+ str(((time.time() - start_time)))+" seconds ---"
                    +"\n" +"--- Run Time = "+str(((time.time() - start_time)/60.0))+" minutes ---"+"\n")

示例#9

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='swedish_leaf',
                          epochs=2000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='swedish_leaf',
                                             batch_size=64)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#10

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='trace',
                          epochs=1000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='trace',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#11

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='phalanges_outline_correct',
                          epochs=2000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='phalanges_outline_correct',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#12

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='NonInvasiveFatalECG_Thorax1',
                          epochs=2000,
                          batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='NonInvasiveFatalECG_Thorax1',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#13

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='proximal_phalanx_outline',
                          epochs=2000,
                          batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='proximal_phalanx_outline',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#14

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='olive_oil',
                          epochs=6000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='olive_oil',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#15

文件： 35-InlineSkate_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='inline_skate',
                          epochs=2000,
                          batch_size=128)

    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='inline_skate',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#16

文件： 6-CBF_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

        model = generate_GRU_FCN_model()
        start_time = time.time()
    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model() 
        start_time = time.time()
    
    history = train_model(model, DATASET_INDEX, dataset_prefix='cbf', epochs=2000, batch_size=32)
    summary = model.summary()
    accuracy, loss,f_score = evaluate_model(model, DATASET_INDEX, dataset_prefix='cbf', batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" % ((time.time() - start_time)/60.0))  
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time ="+ str(((time.time() - start_time)))+" seconds ---"
                    +"\n" +"--- Run Time = "+str(((time.time() - start_time)/60.0))+" minutes ---"+"\n")
    print(history.history.keys())
    
    
    plt.plot(history.history['loss'])
    plt.plot(history.history['loss'])
    plt.xlabel('epoch', fontsize=16)
    plt.xlim(left=0)

示例#17

文件： 14-DiatomSizeReduction_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='diatom_size_reduction',
                          epochs=2000,
                          batch_size=64)
    summary = model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='diatom_size_reduction',
        batch_size=64)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#18

    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()

    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()

    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='electric_devices',
                          epochs=2000,
                          batch_size=128)
    summary = model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='electric_devices',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#19

文件： 26-FiftyWords_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='fifty_words',
                          epochs=2000,
                          batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='fifty_words',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#20

文件： 16-DistalPhalanxOutlineCorrect_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='phalanx_outline_timesequence',
                          epochs=2000,
                          batch_size=128)
    summary = model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='phalanx_outline_timesequence',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#21

文件： 47-MoteStrain_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

        model = generate_GRU_FCN_model()
        start_time = time.time()
    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model() 
        start_time = time.time()
    
    history = train_model(model, DATASET_INDEX, dataset_prefix='mote_strain', epochs=2000, batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model, DATASET_INDEX, dataset_prefix='mote_strain', batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" % ((time.time() - start_time)/60.0))  
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time ="+ str(((time.time() - start_time)))+" seconds ---"
                    +"\n" +"--- Run Time = "+str(((time.time() - start_time)/60.0))+" minutes ---"+"\n")
    print(history.history.keys())
    
    
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.legend(['train', 'validation'], loc='upper right', fontsize ='large')
    plt.xlim(left=0)

示例#22

文件： 30-GunPoint_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='gunpoint',
                          epochs=2000,
                          batch_size=128)

    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='gunpoint',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#23

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='screen_type',
                          epochs=2000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='screen_type',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#24

文件： 61-ShapesAll_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

        start_time = time.time()
    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model() 
        start_time = time.time()


    history = train_model(model, DATASET_INDEX, dataset_prefix='shapes_all', epochs=4000, batch_size=64)
    model.summary()
    accuracy, loss , f_score= evaluate_model(model, DATASET_INDEX, dataset_prefix='shapes_all', batch_size=64)


    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" % ((time.time() - start_time)/60.0))  
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time ="+ str(((time.time() - start_time)))+" seconds ---"
                    +"\n" +"--- Run Time = "+str(((time.time() - start_time)/60.0))+" minutes ---"+"\n")
    print(history.history.keys())
    
    
    plt.plot(history.history['loss'])
    plt.xlabel('epoch', fontsize=16)
    plt.ylabel('loss',fontsize=16)

示例#25

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='worms_two_class',
                          epochs=1000,
                          batch_size=16)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='worms_two_class',
                                             batch_size=16)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#26

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='phenome',
                          epochs=2000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='phenome',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#27

文件： 0-Adiac_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()
    elif select == '6':
        model = generate_model_new()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='adiac',
                          epochs=4000,
                          batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='adiac',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#28

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='toe_segmentation1',
                          epochs=2000,
                          batch_size=64)
    model.summary()
    accuracy, loss, f_score = evaluate_model(
        model,
        DATASET_INDEX,
        dataset_prefix='toe_segmentation1',
        batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +

示例#29

文件： 19-ECG200_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='ecg200',
                          epochs=8000,
                          batch_size=64)
    summary = model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='ecg200',
                                             batch_size=64)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +

示例#30

文件： 60-ShapeletSim_model.py 项目： zhang110112/GRU-FCN-model-for-univariate-time-series-classification

    elif select == '2':
        model = generate_LSTM_FCN_model()
        start_time = time.time()
    elif select == '3':
        model = generate_ALSTM_FCN_model()
        start_time = time.time()
    elif select == '4':
        model = generate_FCN_model()
        start_time = time.time()
    elif select == '5':
        model = generate_MLP_model()
        start_time = time.time()

    history = train_model(model,
                          DATASET_INDEX,
                          dataset_prefix='shapelet_sim',
                          epochs=2000,
                          batch_size=128)
    model.summary()
    accuracy, loss, f_score = evaluate_model(model,
                                             DATASET_INDEX,
                                             dataset_prefix='shapelet_sim',
                                             batch_size=128)

    print("--- Run Time = %s seconds ---" % ((time.time() - start_time)))
    print("--- Run Time = %s minutes ---" %
          ((time.time() - start_time) / 60.0))
    text_file = open("training_time.txt", "w")
    text_file.write("--- Run Time =" + str(((time.time() - start_time))) +
                    " seconds ---" + "\n" + "--- Run Time = " +
                    str(((time.time() - start_time) / 60.0)) + " minutes ---" +