pytorch预训练模型包含多个经典网络,比如resnet系列、vgg系列和alexnet等,预训练模型可以提高网络提取特征的能力,提升训练模型的性能。下面介绍一下加载预训练模型的两种方式:
第一种是在线的方法,即在代码中采用在线加载模式,
import torch
from torchvision import models
model = models.vgg16(pretrained=True)
这样当代码运行到model时,就会根据pytorch中模型的定义找到该模型,并通过url加载预训练模型放在./cache/checkpoints中,需要时就会加载模型参数。
另一种方法是离线加载方式,这需要提前下载好预训练模型,预训练模型的下载可以进入该网站:
https://github.com/pytorch/vision/tree/master/torchvision/models
里面有多个网络的定义,进入相应网络的py文件即可找到加载与效率模型的网址:
比如vgg网络的vgg.py文件打开后可以看到
import torch
import torch.nn as nn
from .utils import load_state_dict_from_url
from typing import Union, List, Dict, Any, cast
__all__ = [
'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
'vgg19_bn', 'vgg19',
]
model_urls = {
'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}
class VGG(nn.Module):
def __init__(
self,
features: nn.Module,
num_classes: int = 1000,
init_weights: bool = True
) -> None:
super(VGG, self).__init__()
self.features = features
self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
self.classifier = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, num_classes),
)
model_urls中注明了多种vgg模型的下载地址,具体下载方法是直接复制网址打开,比如vgg16,复制网址https://download.pytorch.org/models/vgg16-397923af.pth在浏览器中打开,就会自动打开下载界面进行下载,下载好之后放在你当前要运行的文件夹下,其中加载的程序要做一些修改,如下:
....
model = models.vgg16(pretrained=False)#在线模式的True改为False
pre = torch.load('vgg16-397923af.pth')#进行加载
model.load_state_dict(pre)
....
以上就是在线和离线加载预训练模型的两种方法。
**
**
mmdetection有些预训练模型能在上述pytorch网站中找到,但有些就找不到,看名称很接近,我下载过两个这样的pth模型文件,一个名称一致,一个名称不够细节,结果两个文件大小差了很多,显然不是一样的,如果随便用,就可能报错。
于是查找了mmdetection对应的预训练模型加载方法,结果是所有需求的预训练模型都已经总结在mmcv里面了,有直接的下载网址,可直接拉取。
拉取网址:
https://github.com/open-mmlab/mmcv/blob/master/mmcv/model_zoo/open_mmlab.json
下面是打开的mmcv-master/mmcv/model_zoo/open-mmlab.json的具体内容
{
"vgg16_caffe": "https://download.openmmlab.com/pretrain/third_party/vgg16_caffe-292e1171.pth",
"detectron/resnet50_caffe": "https://download.openmmlab.com/pretrain/third_party/resnet50_caffe-788b5fa3.pth",
"detectron2/resnet50_caffe": "https://download.openmmlab.com/pretrain/third_party/resnet50_msra-5891d200.pth",
"detectron/resnet101_caffe": "https://download.openmmlab.com/pretrain/third_party/resnet101_caffe-3ad79236.pth",
"detectron2/resnet101_caffe": "https://download.openmmlab.com/pretrain/third_party/resnet101_msra-6cc46731.pth",
"detectron2/resnext101_32x8d": "https://download.openmmlab.com/pretrain/third_party/resnext101_32x8d-1516f1aa.pth",
"resnext50_32x4d": "https://download.openmmlab.com/pretrain/third_party/resnext50-32x4d-0ab1a123.pth",
"resnext101_32x4d": "https://download.openmmlab.com/pretrain/third_party/resnext101_32x4d-a5af3160.pth",
"resnext101_64x4d": "https://download.openmmlab.com/pretrain/third_party/resnext101_64x4d-ee2c6f71.pth",
"contrib/resnet50_gn": "https://download.openmmlab.com/pretrain/third_party/resnet50_gn_thangvubk-ad1730dd.pth",
"detectron/resnet50_gn": "https://download.openmmlab.com/pretrain/third_party/resnet50_gn-9186a21c.pth",
"detectron/resnet101_gn": "https://download.openmmlab.com/pretrain/third_party/resnet101_gn-cac0ab98.pth",
"jhu/resnet50_gn_ws": "https://download.openmmlab.com/pretrain/third_party/resnet50_gn_ws-15beedd8.pth",
"jhu/resnet101_gn_ws": "https://download.openmmlab.com/pretrain/third_party/resnet101_gn_ws-3e3c308c.pth",
"jhu/resnext50_32x4d_gn_ws": "https://download.openmmlab.com/pretrain/third_party/resnext50_32x4d_gn_ws-0d87ac85.pth",
"jhu/resnext101_32x4d_gn_ws": "https://download.openmmlab.com/pretrain/third_party/resnext101_32x4d_gn_ws-34ac1a9e.pth",
"jhu/resnext50_32x4d_gn": "https://download.openmmlab.com/pretrain/third_party/resnext50_32x4d_gn-c7e8b754.pth",
"jhu/resnext101_32x4d_gn": "https://download.openmmlab.com/pretrain/third_party/resnext101_32x4d_gn-ac3bb84e.pth",
"msra/hrnetv2_w18_small": "https://download.openmmlab.com/pretrain/third_party/hrnetv2_w18_small-b5a04e21.pth",
"msra/hrnetv2_w18": "https://download.openmmlab.com/pretrain/third_party/hrnetv2_w18-00eb2006.pth",
"msra/hrnetv2_w32": "https://download.openmmlab.com/pretrain/third_party/hrnetv2_w32-dc9eeb4f.pth",
"msra/hrnetv2_w40": "https://download.openmmlab.com/pretrain/third_party/hrnetv2_w40-ed0b031c.pth",
"msra/hrnetv2_w48": "https://download.openmmlab.com/pretrain/third_party/hrnetv2_w48-d2186c55.pth",
"bninception_caffe": "https://download.openmmlab.com/pretrain/third_party/bn_inception_caffe-ed2e8665.pth",
"kin400/i3d_r50_f32s2_k400": "https://download.openmmlab.com/pretrain/third_party/i3d_r50_f32s2_k400-2c57e077.pth",
"kin400/nl3d_r50_f32s2_k400": "https://download.openmmlab.com/pretrain/third_party/nl3d_r50_f32s2_k400-fa7e7caa.pth",
"res2net101_v1d_26w_4s": "https://download.openmmlab.com/pretrain/third_party/res2net101_v1d_26w_4s_mmdetv2-f0a600f9.pth",
"regnetx_400mf": "https://download.openmmlab.com/pretrain/third_party/regnetx_400mf-a5b10d96.pth",
"regnetx_800mf": "https://download.openmmlab.com/pretrain/third_party/regnetx_800mf-1f4be4c7.pth",
"regnetx_1.6gf": "https://download.openmmlab.com/pretrain/third_party/regnetx_1.6gf-5791c176.pth",
"regnetx_3.2gf": "https://download.openmmlab.com/pretrain/third_party/regnetx_3.2gf-c2599b0f.pth",
"regnetx_4.0gf": "https://download.openmmlab.com/pretrain/third_party/regnetx_4.0gf-a88f671e.pth",
"regnetx_6.4gf": "https://download.openmmlab.com/pretrain/third_party/regnetx_6.4gf-006af45d.pth",
"regnetx_8.0gf": "https://download.openmmlab.com/pretrain/third_party/regnetx_8.0gf-3c68abe7.pth",
"regnetx_12gf": "https://download.openmmlab.com/pretrain/third_party/regnetx_12gf-4c2a3350.pth",
"resnet50_v1c": "https://download.openmmlab.com/pretrain/third_party/resnet50_v1c-2cccc1ad.pth",
"resnet101_v1c": "https://download.openmmlab.com/pretrain/third_party/resnet101_v1c-e67eebb6.pth",
"mmedit/vgg16": "https://download.openmmlab.com/mmediting/third_party/vgg_state_dict.pth",
"mmedit/res34_en_nomixup": "https://download.openmmlab.com/mmediting/third_party/model_best_resnet34_En_nomixup.pth",
"mmedit/mobilenet_v2": "https://download.openmmlab.com/mmediting/third_party/mobilenet_v2.pth",
"resnest50": "https://download.openmmlab.com/pretrain/third_party/resnest50_d2-7497a55b.pth",
"resnest101": "https://download.openmmlab.com/pretrain/third_party/resnest101_d2-f3b931b2.pth",
"resnest200": "https://download.openmmlab.com/pretrain/third_party/resnest200_d2-ca88e41f.pth",
"darknet53": "https://download.openmmlab.com/pretrain/third_party/darknet53-a628ea1b.pth"
}
文章浏览阅读1.1k次,点赞2次,收藏20次。项目运行环境配置:Jdk1.8 + Tomcat7.0 + Mysql + HBuilderX(Webstorm也行)+ Eclispe(IntelliJ IDEA,Eclispe,MyEclispe,Sts都支持)。项目技术:SSM + mybatis + Maven + Vue 等等组成,B/S模式 + Maven管理等等。环境需要1.运行环境:最好是java jdk 1.8,我们在这个平台上运行的。其他版本理论上也可以。2.IDE环境:IDEA,Eclipse,Myeclipse都可以。_学科竞赛管理系统开发与应用
文章浏览阅读1.5k次。function dx=shuangzhou(t,x,Tmh,Tmp,Mh,Ihx,Ihy,Ihz,Ihxy,Ihxz,Ihyz,Mp,Ipx,Ipy,...Ipz,Ipxy,Ipxz,Ipyz,g,xh,yh,zh,xp,yp,zp,xhp,yhp,zhp,xch,ych,zch,u,v,w,...p,q,r,theta,varphi,Ch,Cp,Kp)A=p*cos(x(1))*cos(x(2..._错误使用+
文章浏览阅读611次。语法结构 1.捕获异常语法结构: 红框:使用try{}块来抛出异常蓝框:使用try{}块来抛出异常橙框:由于对循环体中的异常进行了捕获处理,所以该行代码可以执行 2.try…catch…finally异常处理结构中,try语句块是必须的, catch和finally语句块至少出现一个。 3.注意:如果try语句块包含的是检查时异常,则在没有..._java子异常与父异常如何补获
文章浏览阅读299次。方法1.GameObject中选择Particle System,即可在场景中创建粒子系统对象方法2.先create empty ,再到Component中选择Effects后,选择Particle System,即为该空物体添加了粒子系统组件。_unity particle system 实例化
文章浏览阅读1k次,点赞2次,收藏3次。基本上Bresenham画线算法的思路如下:// 假设该线段位于第一象限内且斜率大于0小于1,设起点为(x1,y1),终点为(x2,y2).// 根据对称性,可推导至全象限内的线段.1.画起点(x1,y1).2.准备画下个点。x坐标增1,判断如果达到终点,则完成。否则,由图中可知,下个要画的点要么为当前点的右邻接点,要么是当前点的右上邻接点.2.1.如果线段ax+by+c=0与x=x1..._easyx线条粗细
文章浏览阅读7.7k次。酷睿i5-1035G1是一款高效的四核SoC,适用于基于Ice -Lake-U 系列的笔记本电脑和超极本 。它集成了四个Sunnycove处理器内核(由于HyperThreading而支持8个线程),主频为1(基本) – 3.7(单核Turbo)GHz。选锐龙i5-1035G1 还是R7 4800U 哪个好 https://list.jd.com/list.html使用Turbo Boost,2个内核可以达到3.6 GHz,所有4个3.3 GHz。据英特尔称,Sunnycove内核的IPC数量增加了1_r74800u和i51035g1哪个好
文章浏览阅读765次。OpenGL SuperBible 7th 源码编译_superbible7-media github
文章浏览阅读794次,点赞14次,收藏18次。wireshark下载、安装、使用教程
文章浏览阅读288次。MXNet 粗糙的使用指南写于2020年3月24日,最新的CUDA版本为10.2MXNet简介MXNet是一个(跟TF与Torch相比特别小众的)多平台神经网络框架。优点:灵活,多平台,可移植性强。工业界常用框架。缺点:复杂,难以入门,基本没有教材。只能依靠代码来学习代码。框架介绍MXNet现在存在两种界面:symbol与gluon。Symbol的设计思路与T..._iou loss mxnet
文章浏览阅读1.3k次。接上一篇文章ipa包砸壳,接下来讲一下代码混淆。混淆代码,我们需要生成两个文件confuse.sh和func.list。confuse.sh是一个脚本文件,里边定义了混淆的一些算法,以及需要混淆方法的路径。func.list是我们列举的一些需要混淆的方法。当然系统的方法不能混淆,不然一些库文件方法没办法正确加载。1、首先,终端cd到文件目录,并且利用指令touch生成这两个文件touch confuse.shtouch func.list不出意外,文件目录里已经有这两个文件了。_ipa包混淆
文章浏览阅读3.3k次,点赞5次,收藏19次。xlabel('\delta');ylabel('AUC');具体符号的对照表参照下图:_matlab微米怎么输入
文章浏览阅读119次。顺序读写指的是按照文件中数据的顺序进行读取或写入。对于文本文件,可以使用fgets、fputs、fscanf、fprintf等函数进行顺序读写。在C语言中,对文件的操作通常涉及文件的打开、读写以及关闭。文件的打开使用fopen函数,而关闭则使用fclose函数。在C语言中,可以使用fread和fwrite函数进行二进制读写。 Biaoge 于2024-03-09 23:51发布 阅读量:7 ️文章类型:【 C语言程序设计 】在C语言中,用于打开文件的函数是____,用于关闭文件的函数是____。