以前，我使用模型手动训练我的模型。由于内存限制，在for循环中使用fit（）对小批量数据进行训练。问题是我无法通过历史访问所有以前的历史。历史，因为它就像每次训练一个新模型，而以前的历史不会存储在任何地方。

当我使用模型时。fit（）在500个批量上，大约7GB的内存会被填满。我使用keras和tensorflow cpu后端。但当我使用生成器时，即使批处理大小为50，也无法放入内存，并被交换到磁盘上。

我正在执行分类，使用224*224图像，我试图微调vgg脸。我使用vgg脸根据这个链接实现： VGG-Face

我正在使用ResNet和SeNet架构，如链接中所述。

def prepare_input_data(self, batch_addresses):
    image = []
    for j in range(len(batch_addresses)):
        img = cv2.imread(batch_addresses[j])
        img = cv2.resize(img, (224, 224))
        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

        img = img - np.array([103.939, 116.779, 123.68])

        image.append(img)

    data = np.array(image)
    data = data.astype('float32')
    data /= 255

    return data


def train_data_generator(self, addresses, labels, batch_size):
    """Train data generator"""
    #Use first %80 of data for training.
    addresses = addresses[: int(0.8 * len(addresses))]
    labels = labels[: int(0.8 * len(labels))]
    total_data = len(addresses)
    while 1:
        for i in range(total_data / batch_size):
            batch_addresses = addresses[i * batch_size: (i + 1) * batch_size]
            batch_labels = labels[i * batch_size: (i + 1) * batch_size]

            data = self.prepare_input_data(batch_addresses)

            batch_labels = np_utils.to_categorical(batch_labels, self.nb_class)

            yield data, batch_labels

def val_data_generator(self, addresses, labels, batch_size):
    """Validation data generator"""
    #Use the last %20 of data for validation
    addresses = addresses[int(0.8 * len(addresses)):]
    labels = labels[int(0.8 * len(labels)):]
    total_data = len(addresses)
    image = []
    while 1:
        for i in range(total_data / batch_size):
            batch_addresses = addresses[i * batch_size: (i + 1) * batch_size]
            batch_labels = labels[i * batch_size: (i + 1) * batch_size]

            data = self.prepare_input_data(batch_addresses)

            batch_labels = np_utils.to_categorical(batch_labels, self.nb_class)

            yield data, batch_labels

def train(self, label_interested_in):
    """Trains the model"""
    #Read training data from json file, and get addresses and labels
    addresses, labels = self.create_address_and_label(label_interested_in)
    batch_size = 50
    train_batch_size = 40
    val_batch_size = 10
    steps = int(len(addresses) / batch_size) + 1
    print(len(addresses), steps)
    #Perform training
    history = self.custom_vgg_model.fit_generator(
        self.train_data_generator(addresses, labels, train_batch_size),
        steps_per_epoch=steps, epochs=self.number_of_epochs,
        verbose=1, validation_data=self.val_data_generator(addresses, labels, val_batch_size),
        validation_steps=steps, initial_epoch=0)

为什么我看到这么高的内存使用率？是因为在keras中发电机的工作方式吗？我听说生成器预先准备批次，通过与训练并行运行来加速训练过程。还是我做错了什么？

作为一个附带问题，由于fit_generator（）中没有batch_size参数，因此我假设数据基于生成器加载到模型中，并且在加载每个训练和验证批后执行梯度更新，这是否正确？