Question

我正在训练一种机器学习模型，其中包含使用Keras和Tensorflow的两个完全连接的层。在执行详尽搜索以调整某些超参数时，我为每组超参数创建了一个新模型。尽管如此，模型的训练时间在每次迭代时都会增加。为了解决此问题，我每次使用 K.clear_session（）清除Keras会话。

如果我使用CPU运行代码，则代码运行正常。但是，当尝试在Tensorflow后端使用GPU时，应用程序突然崩溃，没有任何警告或错误。

以下是我用来创建新模型的功能。

def get_compiled_model(model_def, shape, model_type='ann'):

    K.clear_session()  #Clear the previous tensorflow graph
    #tf.reset_default_graph()

    #Shared parameters for the models
    optimizer = Adam(lr=0, beta_1=0.5)
    lossFunction = "mean_squared_error"
    metrics = ["mse"]
    model = None

    #Create and compile the models

    if model_type=='ann':
        model = model_def(shape)
        model.compile(optimizer = optimizer, loss = lossFunction, metrics = metrics)
    else:
        pass

    return model

models = {'shallow-20':RULmodel_SN_5}

这是调用上面函数

的代码部分

for dataset_number in max_window_size:

    tunable_model.data_handler.change_dataset(dataset_number)

    verbose = 1

    for r in range(90, 141):   #Load max_rul first as it forces reloading the dataset from file

        verbose = 2
        tunable_model.data_handler.max_rul = r

        for w in range(15, max_window_size[dataset_number]+1):

            for s in range(1,11):

                print("Testing for w:{}, s:{}, r:{}".format(w, s, r))

                #Set data parameters
                tunable_model.data_handler.sequence_length = w
                tunable_model.data_handler.sequence_stride = s

                #Create and compile the models
                shape = num_features*w
                **model = get_compiled_model(models['shallow-20'], shape, model_type='ann')**

                #Add model to tunable model
                tunable_model.change_model('ModelRUL_SN', model, 'keras')

                #Load the data
                tunable_model.load_data(unroll=True, verbose=verbose, cross_validation_ratio=0)

清除Keras会话后，应用程序仍在继续

0 个答案: