random_split() 函数说明

torch.utils.data.random_split(dataset, lengths, generator=<torch._C.Generator object>)

参数

注:关于torch.Generator详见笔记Pytorch:torch.Generator()

pytorch: random_split(),函数的具体定义如下

def random_split(dataset, lengths):
    r"""
    Randomly split a dataset into non-overlapping new datasets of given lengths.

    Arguments:
        dataset (Dataset): Dataset to be split
        lengths (sequence): lengths of splits to be produced
    """
    if sum(lengths) != len(dataset):
        raise ValueError("Sum of input lengths does not equal the length of the input dataset!")

    indices = randperm(sum(lengths)).tolist()
    return [Subset(dataset, indices[offset - length:offset]) for offset, length in zip(_accumulate(lengths), lengths)]

以U-Net代码(详见:U-Net代码复现为例

n_val = int(len(dataset) * val_percent)
n_train = len(dataset) - n_val
train_set, val_set = random_split(dataset, [n_train, n_val], generator=torch.Generator().manual_seed(0))

通过random_split()将数据分为训练集和验证集(随机

原文地址:https://blog.csdn.net/weixin_42046845/article/details/134671637

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任

如若转载,请注明出处:http://www.7code.cn/show_26954.html

如若内容造成侵权/违法违规/事实不符,请联系代码007邮箱suwngjj01@126.com进行投诉反馈,一经查实,立即删除

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注