将数据加载器中的图像拆分为补丁

发布于 2025-01-19 22:59:39 字数 443 浏览 1 评论 0原文

使用 Fashion mnist 数据集，我不想只将单个图像分割为补丁，而是将所有图像分割为多个图像。

我已经看到了函数unfold()，但我认为这只适用于单个图像

mnist_train = torchvision.datasets.FashionMNIST(
root="../data", train=True, 
transform=transforms.Compose([transforms.ToTensor()]), download=True)

x = mnist_train[0][0][-1, :, :]

x = x.unfold(0, 7, 7).unfold(1, 7, 7)

x.shape

如何为所有图像制作不重叠的补丁（任意数量以保持简单）？

将不胜感激任何帮助。谢谢！

原文

Using the Fashion mnist dataset, I don't want to just split a single image into patches but rather all of images.

I've seen the function unfold() but I think this only works for a single image

mnist_train = torchvision.datasets.FashionMNIST(
root="../data", train=True, 
transform=transforms.Compose([transforms.ToTensor()]), download=True)

x = mnist_train[0][0][-1, :, :]

x = x.unfold(0, 7, 7).unfold(1, 7, 7)

x.shape

How do I make non-overlapping patches (of any number to keep it simple) for all images?

Would appreciate any help. Thanks!

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

二智少女 2025-01-26 22:59:39

您可以创建自定义转换以将所有图像分割成多个补丁。大致如下：

class Patch(object):
    """
    Creates patches from images
    """

    def __init__(self, patch_size=7):
        self.patch_size = patch_size

    def __call__(self, image):
        patched_image = # ... your code here
        return patched_image


mnist_train = torchvision.datasets.FashionMNIST(
    root="../data", train=True,
    transform=transforms.Compose([transforms.ToTensor(), Patch()]), download=True)

You can create a custom transform to split all images into multiple patches. Something along the lines of:

class Patch(object):
    """
    Creates patches from images
    """

    def __init__(self, patch_size=7):
        self.patch_size = patch_size

    def __call__(self, image):
        patched_image = # ... your code here
        return patched_image


mnist_train = torchvision.datasets.FashionMNIST(
    root="../data", train=True,
    transform=transforms.Compose([transforms.ToTensor(), Patch()]), download=True)

回复收藏 0 原文

~没有更多了~