TensorFlow/Keras 拆分训练和验证数据

Question

我正在学习如何使用 TensorFlow，并获得了一个构建在 Keras 结构中的工作模型。它运行但结果对我来说有点神秘。我试图复制它并将其简化为它的本质，然后再次构建它。我完全无法理解的部分是 how/where 它将训练数据输入拆分为训练集和验证集？我检查了模型代码、初始参数等。TensorFlow 卷积神经网络中是否有自动执行此操作的内置函数？

对 Talos 的调用如下所示，前两个值是 x-training 和 y-training 值，没有任何地方 x_val 或 y_val 传递给 Talos 函数。 Talos 可以自动生成 x_val 和 y_val 吗？

jam1 = talos.Scan(features3,
                  label2[0,],
                  model = DLAt,
                  params = ParamsJam1,
                  experiment_name = "toy1",
                  fraction_limit=.2)

def DLAt(x_train, y_train, x_val, y_val, params):
    model = Sequential()
    convLayer = Conv1D(filters=params['numFilters'],
                     kernel_size=params['kernalLen'], strides=1, activation='relu',
                     input_shape=(300,4), use_bias=True)
    model.add(convLayer)
    model.add(MaxPooling1D(pool_size=params['maxpool']))
    model.add(Flatten())
    firstHidden = Dense(params['neuronsInLayerOne'], activation='relu',
                  kernel_regularizer=regularizers.l1_l2(l1=params['l1'], l2=0))
    model.add(firstHidden)
    model.add(Dropout(params['dropoutLevel']))
    model.add(Dense(params['neuronsInLayerTwo'], activation='relu'))
    model.add(Dropout(params['dropoutLevel']))
    model.add(Dense(1, activation='sigmoid')) 
    opt = keras.optimizers.Adam(lr=params['lr'])
    model.compile(optimizer = opt, loss = 'loss', metrics = ['mse'])
    out = model.fit(x_train, y_train, epochs = params['epoch'],
                  batch_size =params['batches'],
                  validation_data =(x_val,  y_val))
    return out, model

Answer 1

它根本没有拆分训练数据，您通过参数 validation_data:

明确地将验证数据传递给 model.fit

out = model.fit(x_train, y_train, epochs = params['epoch'],
                  batch_size =params['batches'],
                  validation_data =(x_val,  y_val))

如果你想拆分你的训练数据，不想提供验证数据，你可以使用model.fit(...)中的validation_split参数，这是要使用的训练数据的分数作为验证数据.. default，它被设置为 0.0.

更新 1：检查来源 code of talos.Scan, it uses a validation_split of 0.3 by default. Also, check this。那么它应该是 self-explanatory.

TensorFlow/Keras 拆分训练和验证数据

TensorFlow / Keras splitting training and validation data

python

tensorflow

keras

talos