python - Keras fit_generator 问题

Question

我关注了this tutorial为我的 Keras 模型创建自定义生成器。这是一个显示我面临的问题的 MWE:

import sys, keras
import numpy as np
import tensorflow as tf
import pandas as pd
from keras.models import Model
from keras.layers import Dense, Input
from keras.optimizers import Adam
from keras.losses import binary_crossentropy

class DataGenerator(keras.utils.Sequence):
    'Generates data for Keras'
    def __init__(self, list_IDs, batch_size, shuffle=False):
        'Initialization'
        self.batch_size = batch_size
        self.list_IDs = list_IDs
        self.shuffle = shuffle
        self.on_epoch_end()

    def __len__(self):
        'Denotes the number of batches per epoch'
        return int(np.floor(len(self.list_IDs) / self.batch_size))

    def __getitem__(self, index):
        'Generate one batch of data'
        # Generate indexes of the batch
        #print('self.batch_size: ', self.batch_size)
        print('index: ', index)
        sys.exit()

    def on_epoch_end(self):
        'Updates indexes after each epoch'
        self.indexes = np.arange(len(self.list_IDs))
        print('self.indexes: ', self.indexes)
        if self.shuffle == True:
            np.random.shuffle(self.indexes)

    def __data_generation(self, list_IDs_temp):
        'Generates data containing batch_size samples' # X : (n_samples, *dim, n_channels)

        X1 = np.empty((self.batch_size, 10), dtype=float)
        X2 = np.empty((self.batch_size, 12),  dtype=int)

        #Generate data
        for i, ID in enumerate(list_IDs_temp):
            print('i is: ', i, 'ID is: ', ID)

            #Preprocess this sample (omitted)
            X1[i,] = np.repeat(1, X1.shape[1])
            X2[i,] = np.repeat(2, X2.shape[1])

        Y = X1[:,:-1]
        return X1, X2, Y

if __name__=='__main__':
    train_ids_to_use = list(np.arange(1, 321)) #1, 2, ...,320 
    valid_ids_to_use = list(np.arange(321, 481)) #321, 322, ..., 480

    params = {'batch_size': 32}

    train_generator = DataGenerator(train_ids_to_use, **params)
    valid_generator = DataGenerator(valid_ids_to_use, **params)

    #Build a toy model
    input_1 = Input(shape=(3, 10))
    input_2 = Input(shape=(3, 12))
    y_input = Input(shape=(3, 10))

    concat_1 = keras.layers.concatenate([input_1, input_2])
    concat_2 = keras.layers.concatenate([concat_1, y_input])

    dense_1 = Dense(10, activation='relu')(concat_2)
    output_1 = Dense(10, activation='sigmoid')(dense_1)

    model = Model([input_1, input_2, y_input], output_1)
    print(model.summary())

    #Compile and fit_generator
    model.compile(optimizer=Adam(lr=0.001), loss=binary_crossentropy)
    model.fit_generator(generator=train_generator, validation_data = valid_generator, epochs=2, verbose=2)

我不想打乱我的输入数据。我以为这已经得到处理，但在我的代码中，当我在 __get_item__ 中打印出 index 时，我得到了随机数。我想要连续的数字。请注意，我正在尝试使用 __getitem__ 中的 sys.exit 终止进程，以查看发生了什么。

我的问题:

1. 为什么index不连续？我该如何解决这个问题？

2. 当我在终端使用 screen 运行它时，为什么它不响应 Ctrl+C？

Answer 1

您可以使用fit_generator 方法的shuffle 参数来连续生成批处理。来自 fit_generator() documentation :

shuffle: Boolean. Whether to shuffle the order of the batches at the beginning of each epoch. Only used with instances of Sequence (keras.utils.Sequence). Has no effect when steps_per_epoch is not None.

只需将 shuffle=False 传递给 fit_generator:

model.fit_generator(generator=train_generator, shuffle=False, ...)