【踩坑日记29】UserWarning: Arguments other than a weight enum or `None` for ‘weights‘ are deprecated since

问题描述

UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.

问题分析

from torchvision import models
model_old = models.vgg16(pretrained=True)

原始代码中pretrained=True已经弃用,要使用weights=VGG16_Weights.IMAGENET1K_V1(指定权重版本)或者weights=VGG16_Weights.DEFAULT(权重选择最新版本)

问题解决

代码改为:

from torchvision import models
model_old = models.vgg16(weights=models.VGG16_Weights.IMAGENET1K_V1)

参考

UserWarning: Arguments other than a weight enum or None for ‘weights‘ are deprecated since 0.13 an
【PyTorch教程】04-详解torchvision 0.13中的预训练模型加载的更新及报错的解决方法 (2022年最新)

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值