【warning】UserWarning: The parameter ‘pretrained‘ is deprecated since 0.13 and may be removed

import torchvision.models as models
self.backbone = models.resnet101(pretrained=True) #旧版本写法

报错内容：

C:\Users\ting\anaconda3\envs\pytorch\python.exe C:\Users\Administrator\PycharmProjects\FCN\model\fcn_res101.py
C:\Users\ting\anaconda3\envs\pytorch\lib\site-packages\torchvision\models\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.warnings.warn(
C:\Users\ting\anaconda3\envs\pytorch\lib\site-packages\torchvision\models\_utils.py:223: 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=ResNet101_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet101_Weights.DEFAULT` to get the most up-to-date weights.warnings.warn(msg)
torch.Size([1, 21, 256, 256])Process finished with exit code 0

翻译一下，就是参数列表中的pretrained在新版本中被弃了，要使用weights这个参数。然后教你用新的参数。

就按照watning里写的把models.resnet101()后面的内容重新设置就好。

第一种：weights = models.ResNet101_Weights.DEFAULT

import torchvision.models as models
self.backbone = models.resnet101(weights = models.ResNet101_Weights.DEFAULT)

输出结果：

C:\Users\ting\anaconda3\envs\pytorch\python.exe C:\Users\Administrator\PycharmProjects\FCN\model\fcn_res101.py
Downloading: "https://download.pytorch.org/models/resnet101-cd907fc2.pth" to C:\Users\Administrator/.cache\torch\hub\checkpoints\resnet101-cd907fc2.pth
100%|██████████| 171M/171M [00:42<00:00, 4.17MB/s]
torch.Size([1, 21, 256, 256])Process finished with exit code 0

第二种：weights = models.ResNet101_Weights.IMAGENET1K_V1

import torchvision.models as models
self.backbone = models.resnet101(weights = models.ResNet101_Weights.IMAGENET1K_V1)

输出结果：

C:\Users\ting\anaconda3\envs\pytorch\python.exe C:\Users\Administrator\PycharmProjects\FCN\model\fcn_res101.py
torch.Size([1, 21, 256, 256])Process finished with exit code 0

res101中weight官方解释

【warning】UserWarning: The parameter ‘pretrained‘ is deprecated since 0.13 and may be removed相关推荐

【Zabbix】CentOS6.9系统下部署Zabbix-server 3.0
[Zabbix]CentOS6.9系统下部署Zabbix-server 3.0 目录安装Zabbix 关闭selinux 删除旧版本MySQL5.1数据库安装MySQL 5.6数据库安装PHP ...
【TensorRT】TensorRT was linked against cudnn 8.6.0 but loaded cudnn 8.3.2
[TensorRT]TensorRT was linked against cudnn 8.6.0 but loaded cudnn 8.3.2 1 电脑环境 2 问题描述 3 直接原因 4 解决办法 ...
工程之星位置服务器,【收藏】操作步骤：工程之星5.0在道路上的应用之平曲线设计交点法...
原标题:[收藏]操作步骤:工程之星5.0在道路上的应用之平曲线设计交点法现在,RTK被广泛应用于道路工程的测量,我们在修一条公路,无非就是要测这条路的中线.边线.开挖线.横断面等,工程之星5.0的道 ...
MySQL初始化zabbix_【Zabbix】CentOS6.9系统下部署Zabbix-server 3.0
[TOC] ## 安装Zabbix ### 关闭selinux ```bash [root@localhost ~]# sed -i "s#SELINUX=enforcing#SELINUX ...
【Zabbix】使用dbforbbix 2.2-beta监控Redhat 7.0上的Oracle、Mysql
前言 zabbix 3.4 + DBforBIX 2.2-beta 监控 Oracle.Mysql 前置条件:已安装 zabbix 3.4 ([Zabbix]yum方式安装zabbix) 前置条件:能 ...
【汇总】多种方法教你绕过 TPM 2.0 安装 Windows 11 操作系统
此前我们曾介绍三种方法绕过 TPM 2.0 来安装 Windows 11 操作系统. 方法一:删除 appraiserres.dll 文件方法二:替换 appraiserres.dll 文件方法三 ...
【kafka】Replication factor: 1 larger than available brokers:0
文章目录 1.概述 1.概述文章重复了:[Kafka]kafka replication factor : 3 larger than avaiable brokers:2 kafka现在一创建消费 ...
【5】基于VS2017的MFC平台与OpenCV4.0.1联合小案列
最近由于要做项目所以做可视化界面,在网上查询了半天时间发现大部分MFC和OpenCV联合开发的案例都是基于OpenCV3.0以前,较为新的版本较少或者制作过程不清楚.为此本人将自己查阅资料写的基于VS ...
【Web】Web内容可访问性指南 1.0
为什么80%的码农都做不了架构师?>>> 译文:Web内容可访问性指南 1.0 http://www.junchenwu.com/WAI/wai-pageauth.html原文 ...
【Python】UserWarning: image file could not be identified because WEBP support not installed
最近在研究使用Python进行图片裁剪的功能,发现Python的PIL模块在处理图片上有不可替代的优势,但是在使用open()方法加载图片时却报了如下的错误: D:\anaconda\lib\site ...

【warning】UserWarning: The parameter ‘pretrained‘ is deprecated since 0.13 and may be removed

【warning】UserWarning: The parameter ‘pretrained‘ is deprecated since 0.13 and may be removed相关推荐

最新文章

热门文章