时间戳

首页 > 解决方案 > DataGenerator(Sequence) 无需调整大小

python - DataGenerator(Sequence) 无需调整大小

问题描述

我创建了一个DataGenerator(Sequence)定义batch_size,batch_x和batch_y. batch_x是一批图像（来自x_set，图像的文件路径列表），由 读取imread、调整大小resize并除以 255 以获得介于 0 和 1 之间的值。batch_y是这些图像的标签，它们来自y_set，a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。所以，这不再是必要的了，我现在想修改DataGenerator并保留该resize功能。这是我的代码DataGenerator_withoutresize(Sequence)：

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

这段代码正确吗？

谢谢！

标签： pythongenerator

解决方案

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

推荐阅读