dalian-university/秀水分区/model/model_keras_base.py

# -*- coding: UTF-8 -*-
from keras.layers import Input, Dense, LSTM, concatenate, Conv1D, Conv2D, MaxPooling1D, Reshape, Flatten
from keras.models import Model, load_model
from keras.callbacks import ModelCheckpoint, EarlyStopping
from keras import optimizers
from keras.callbacks import TensorBoard
import matplotlib.pyplot as plt
import numpy as np
from keras.callbacks import TensorBoard, EarlyStopping


# model_history = model.fit_generator(train_generator, epochs=30, validation_data=evaluate_generator,
#                                     callbacks=[early_stopping, tbCallBack])


def get_keras_model(opt):
    lstm_input = Input(shape=(opt.Model['time_step'], opt.input_size_lstm))
    lstm = lstm_input
    for i in range(opt.Model['lstm_layers']):
        rs = True
        if i == opt.Model['lstm_layers']-1:
            rs = False
        lstm = LSTM(units=opt.Model['hidden_size'], return_sequences=rs)(lstm)

    lstm = Dense(16)(lstm)
    # lstm = Flatten()(lstm)
    # lstm = concatenate([lstm, cnn])
    # lstm = Dense(16)(lstm)
    # lstm = Flatten()(lstm)
    # output = Dense(opt.output_size)(lstm)
    model = Model(lstm_input, lstm)
    adam = optimizers.adam(lr=0.01, beta_1=0.9, beta_2=0.999, epsilon=1e-7, amsgrad=True)
    model.compile(loss='mse', optimizer='adam')
    return model


def train_init(use_cuda=False):
    import tensorflow as tf
    from keras.backend.tensorflow_backend import set_session
    if use_cuda:
        # gpu init
        sess_config = tf.ConfigProto(log_device_placement=True, allow_soft_placement=True)
        sess_config.gpu_options.per_process_gpu_memory_fraction = 0.7  # 最多使用70%GPU内存
        sess_config.gpu_options.allow_growth=True   # 初始化时不全部占满GPU显存, 按需分配
        sess = tf.Session(config=sess_config)
        set_session(sess)
    else:
        session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
        tf.set_random_seed(1234)
        sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
        set_session(sess)


def train(opt, train_and_valid_data):
    train_init(opt.use_cuda)
    train_X, train_Y, valid_X, valid_Y = train_and_valid_data
    print("----------", np.array(train_X[0]).shape)
    print("++++++++++", np.array(train_X[1]).shape)
    model = get_keras_model(opt)
    model.summary()
    weight_lstm_1, bias_lstm_1 = model.get_layer('dense_1').get_weights()
    print("weight_lstm_1 = ", weight_lstm_1)
    print("bias_lstm_1 = ", bias_lstm_1)
    if opt.add_train:
        model.load_weights(opt.model_save_path + 'model_kerass.h5')

    check_point = ModelCheckpoint(filepath=opt.model_save_path + opt.save_name, monitor='val_loss',
                                    save_best_only=True, mode='auto')
    early_stop = EarlyStopping(monitor='val_loss', patience=opt.Model['patience'], mode='auto')

    history = model.fit(train_X, train_Y, batch_size=opt.Model['batch_size'], epochs=opt.Model['epoch'], verbose=2,
              validation_data=(valid_X, valid_Y), callbacks=[check_point, early_stop])

    # acc = history.history['acc']
    loss = history.history['loss']
    epochs = range(1, len(loss) + 1)
    plt.title('Loss')
    # plt.plot(epochs, acc, 'red', label='Training acc')
    plt.plot(epochs, loss, 'blue', label='Validation loss')
    plt.legend()
    # plt.show()

def predict(config, test_X):
    model = get_keras_model(config)
    model.load_weights(config.model_save_path + config.save_name)
    result = model.predict(test_X, batch_size=1)
    # result = result.reshape((-1, config.output_size))
    return result


def predict_cls(config, test_X, df_Y):
    results, results1, results2, results3, results4 = [], [], [], [], []
    dfy1, dfy2, dfy3, dfy4 = [], [], [],[]
    model = get_keras_model(config)
    model1 = get_keras_model(config)
    for i, X in enumerate(zip(test_X[0], test_X[1])):
        X = [np.array([X[0]]), np.array([X[1]])]
        # X = np.array([X[1]])
        print("label=", df_Y[i]['label'][0])
        if df_Y[i]['label'][0] == 1:
            model1.load_weights('./checkpoint/model_keras.h5/' + 'model_keras1.h5')
            result = model1.predict(X, batch_size=1)
            results1.append(result[0])
            results.append(result[0])
            dfy1.append(df_Y[i])
        elif df_Y[i]['label'][0] == 2:
            model.load_weights('./checkpoint/model_keras.h5/' + 'model_keras2.h5')
            result = model.predict(X, batch_size=1)
            results2.append(result[0])
            results.append(result[0])
            dfy2.append(df_Y[i])
        elif df_Y[i]['label'][0] == 3:
            model.load_weights('./checkpoint/model_keras.h5/' + 'model_keras3.h5')
            result = model.predict(X, batch_size=1)
            results3.append(result[0])
            results.append(result[0])
            dfy3.append(df_Y[i])
        elif df_Y[i]['label'][0] == 4:
            model.load_weights('./checkpoint/model_keras.h5/' + 'model_keras4.h5')
            result = model.predict(X, batch_size=1)
            results4.append(result[0])
            results.append(result[0])
            dfy4.append(df_Y[i])
    # result = result.reshape((-1, config.output_size))
    return np.array(results), np.array(results1), np.array(results2), np.array(results3), np.array(results4), dfy1, dfy2, dfy3, dfy4