不调整大小的 DataGenerator(Sequence)

Question

我创建了一个 class DataGenerator(Sequence)，它定义了 batch_size、batch_x 和 batch_y。 batch_x 是由 imread 读取的图像批次（来自 x_set，图像的文件路径列表），按 resize 调整大小并除以 255为了获得 0 和 1 之间的值。batch_y 是这些图像的标签，来自 y_set，一个包含所有标签的列表。

class DataGenerator(Sequence):

    def __init__(self, x_set, y_set, batch_size):
        self.x, self.y = x_set, y_set
        self.batch_size = batch_size

    def __len__(self):
        return math.ceil(len(self.x) / self.batch_size)

    def __getitem__(self, idx):
        batch_x = self.x[idx*self.batch_size : (idx + 1)*self.batch_size]
        batch_x = np.array([resize(imread(file_name), (64, 128)) for file_name in batch_x])
        batch_x = batch_x * 1./255
        batch_y = self.y[idx*self.batch_size : (idx + 1)*self.batch_size]
        batch_y = np.array(batch_y)

        return batch_x, batch_y

因为这个生成器可以工作但在 Colab 上需要很长时间，所以我之前调整了图像的大小。因此，这不再是必需的，我现在想修改 DataGenerator 并保留 resize 函数。这是我的 DataGenerator_withoutresize(Sequence):

代码

class DataGenerator_withoutresize(Sequence):

    def __init__(self, x_set, y_set, batch_size):
        self.x, self.y = x_set, y_set
        self.batch_size = batch_size

    def __len__(self):
        return math.ceil(len(self.x) / self.batch_size)

    def __getitem__(self, idx):
        batch_x = self.x[idx*self.batch_size : (idx + 1)*self.batch_size]
        batch_x = np.array([(imread(file_name) for file_name in batch_x])
        batch_x = batch_x * 1./255
        batch_y = self.y[idx*self.batch_size : (idx + 1)*self.batch_size]
        batch_y = np.array(batch_y)

        return batch_x, batch_y

这个代码正确吗？

谢谢！

Answer 1

最后，我使用了这段代码，它对我有用：

class DataGenerator(Sequence):

    def __init__(self, x_set, y_set, batch_size):
        self.x, self.y = x_set, y_set
        self.batch_size = batch_size

    def __len__(self):
        return math.ceil(len(self.x) / self.batch_size)

    def __getitem__(self, idx):
        batch_x = self.x[idx*self.batch_size : (idx + 1)*self.batch_size]
        batch_x = [imread(file_name) for file_name in batch_x]
        batch_x = np.array(batch_x)
        batch_x = batch_x * 1./255
        batch_y = self.y[idx*self.batch_size : (idx + 1)*self.batch_size]
        batch_y = np.array(batch_y)

        return batch_x, batch_y

不调整大小的 DataGenerator(Sequence)

DataGenerator(Sequence) without resize

python

generator