如何在tensorlayer中加载本地数据

Question

如何更改加载tensorlayer的cifar10dataset的代码：

# The data, shuffled and split between train and test sets
    self.x_train, self.y_train, self.x_test, self.y_test = tl.files.load_cifar10_dataset(shape=(-1, 32, 32, 3), plotable=False)

加载具有780x780像素和RGB的本地文件

Answer 1

TensorLayer提供了一个API来加载本地数据。

# load a list of PNG image files name
train_img_list = tl.files.load_file_list(path="image_folder", regx='.*.png', printable=False)
# read all images
images = tl.vis.read_images(train_img_list, path="image_folder", n_threads=32)

之后，您可以使用tl.prepro工具箱根据需要调整所有图像的大小。http://tensorlayer.readthedocs.io/en/latest/modules/prepro.html

参考：

SRGAN main

tl.vis.read_images