VGG16

最新推荐文章于 2024-06-25 09:18:44 发布
最新推荐文章于 2024-06-25 09:18:44 发布
阅读量2.8k 收藏 3
点赞数 3
分类专栏： Caffe
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/raby_gyl/article/details/79428737
版权

Models from the BMVC-2014 paper “Return of the Devil in the Details: Delving Deep into Convolutional Nets”

The models are trained on the ILSVRC-2012 dataset. The details can be found on the project page or in the following BMVC-2014 paper:

Return of the Devil in the Details: Delving Deep into Convolutional
Nets K. Chatfield, K. Simonyan, A. Vedaldi, A. Zisserman British
Machine Vision Conference, 2014 (arXiv ref. cs1405.3531)

Please cite the paper if you use the models.

Models:

VGG_CNN_S: 13.1% top-5 error on ILSVRC-2012-val
VGG_CNN_M: 13.7% top-5 error on ILSVRC-2012-val
VGG_CNN_M_2048: 13.5% top-5 error on ILSVRC-2012-val
VGG_CNN_M_1024: 13.7% top-5 error on ILSVRC-2012-val
VGG_CNN_M_128: 15.6% top-5 error on ILSVRC-2012-val
VGG_CNN_F: 16.7% top-5 error on ILSVRC-2012-val

Models used by the VGG team in ILSVRC-2014
The models are the improved versions of the models used by the VGG team in the ILSVRC-2014 competition. The details can be found on the project page or in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition K.
Simonyan, A. Zisserman arXiv:1409.1556

Please cite the paper if you use the models.

Models:

16-layer: 7.5% top-5 error on ILSVRC-2012-val, 7.4% top-5 error on ILSVRC-2012-test
19-layer: 7.5% top-5 error on ILSVRC-2012-val, 7.3% top-5 error on ILSVRC-2012-test

In the paper, the models are denoted as configurations D and E, trained with scale jittering. The combination of the two models achieves 7.1% top-5 error on ILSVRC-2012-val, and 7.0% top-5 error on ILSVRC-2012-test.

VGG16 for face recognition: caffemodel,
http://www.robots.ox.ac.uk/~vgg/software/vgg_face/

注释：
gist.github.com 被墙无法访问解决办法
windows下 打开C:\Windows\System32\drivers\etc\hosts文件
编辑器打开，在最后行添加192.30.253.118 gist.github.com
保存。

从头开始训练，将参数的“gaussian”初始方式 修改为“xavier”, 否则训练的时候可能不会收敛。参数的初始化方式很重要。

train.prototxt

layer {
  name: "data"
  type: "Python"
  top: "Features"
  top: "Headposes"
  python_param {
    module: "python_read_data_for_softmax"
    layer: "AllDataLayer"
    param_str: "{\'phase\': \'train\', \'dataset_name\': \'lfw\', \'data_type\': \'image\',\'batch_size\': 48,\'cross_id\':0}"
  }
}

layer {  
  bottom: "Features"  
  top: "conv1_1"  
  name: "conv1_1"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 64  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv1_1"  
  top: "conv1_1"  
  name: "relu1_1"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv1_1"  
  top: "conv1_2"  
  name: "conv1_2"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 64  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv1_2"  
  top: "conv1_2"  
  name: "relu1_2"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv1_2"  
  top: "pool1"  
  name: "pool1"  
  type: "Pooling"  
  pooling_param {  
    pool: MAX  
    kernel_size: 2  
    stride: 2  
  }  
}  
layer {  
  bottom: "pool1"  
  top: "conv2_1"  
  name: "conv2_1"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 128  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv2_1"  
  top: "conv2_1"  
  name: "relu2_1"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv2_1"  
  top: "conv2_2"  
  name: "conv2_2"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 128  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv2_2"  
  top: "conv2_2"  
  name: "relu2_2"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv2_2"  
  top: "pool2"  
  name: "pool2"  
  type: "Pooling"  
  pooling_param {  
    pool: MAX  
    kernel_size: 2  
    stride: 2  
  }  
}  
layer {  
  bottom: "pool2"  
  top: "conv3_1"  
  name: "conv3_1"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 256  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv3_1"  
  top: "conv3_1"  
  name: "relu3_1"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv3_1"  
  top: "conv3_2"  
  name: "conv3_2"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 256  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv3_2"  
  top: "conv3_2"  
  name: "relu3_2"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv3_2"  
  top: "conv3_3"  
  name: "conv3_3"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 256  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv3_3"  
  top: "conv3_3"  
  name: "relu3_3"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv3_3"  
  top: "pool3"  
  name: "pool3"  
  type: "Pooling"  
  pooling_param {  
    pool: MAX  
    kernel_size: 2  
    stride: 2  
  }  
}  
layer {  
  bottom: "pool3"  
  top: "conv4_1"  
  name: "conv4_1"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 512  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv4_1"  
  top: "conv4_1"  
  name: "relu4_1"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv4_1"  
  top: "conv4_2"  
  name: "conv4_2"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 512  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv4_2"  
  top: "conv4_2"  
  name: "relu4_2"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv4_2"  
  top: "conv4_3"  
  name: "conv4_3"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 512  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv4_3"  
  top: "conv4_3"  
  name: "relu4_3"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv4_3"  
  top: "pool4"  
  name: "pool4"  
  type: "Pooling"  
  pooling_param {  
    pool: MAX  
    kernel_size: 2  
    stride: 2  
  }  
}  
layer {  
  bottom: "pool4"  
  top: "conv5_1"  
  name: "conv5_1"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 512  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv5_1"  
  top: "conv5_1"  
  name: "relu5_1"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv5_1"  
  top: "conv5_2"  
  name: "conv5_2"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 512  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv5_2"  
  top: "conv5_2"  
  name: "relu5_2"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv5_2"  
  top: "conv5_3"  
  name: "conv5_3"  
  type: "Convolution"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  convolution_param {  
    num_output: 512  
    pad: 1  
    kernel_size: 3  
    weight_filler {  
      type: "xavier"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  
layer {  
  bottom: "conv5_3"  
  top: "conv5_3"  
  name: "relu5_3"  
  type: "ReLU"  
}  
layer {  
  bottom: "conv5_3"  
  top: "pool5"  
  name: "pool5"  
  type: "Pooling"  
  pooling_param {  
    pool: MAX  
    kernel_size: 2  
    stride: 2  
  }  
}  
layer {  
  bottom: "pool5"  
  top: "fc6"  
  name: "fc6"  
  type: "InnerProduct"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  inner_product_param {  
    num_output: 4096  
    weight_filler {  
      type: "xavier"  
      std: 0.005  
    }  
    bias_filler {  
      type: "constant"  
      value: 0.1  
    }  
  }  
}  
layer {  
  bottom: "fc6"  
  top: "fc6"  
  name: "relu6"  
  type: "ReLU"  
}  
layer {  
  bottom: "fc6"  
  top: "fc6"  
  name: "drop6"  
  type: "Dropout"  
  dropout_param {  
    dropout_ratio: 0.5  
  }  
}  
layer {  
  bottom: "fc6"  
  top: "fc7"  
  name: "fc7"  
  type: "InnerProduct"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  inner_product_param {  
    num_output: 4096  
    weight_filler {  
      type: "xavier"  
      std: 0.005  
    }  
    bias_filler {  
      type: "constant"  
      value: 0.1  
    }  
  }  
}  
layer {  
  bottom: "fc7"  
  top: "fc7"  
  name: "relu7"  
  type: "ReLU"  
}  
layer {  
  bottom: "fc7"  
  top: "fc7"  
  name: "drop7"  
  type: "Dropout"  
  dropout_param {  
    dropout_ratio: 0.5  
  }  
}  
layer {  
  bottom: "fc7"  
  top: "fc8"  
  name: "fc8"  
  type: "InnerProduct"  
  param {  
    lr_mult: 1  
    decay_mult: 1  
  }  
  param {  
    lr_mult: 2  
    decay_mult: 0  
  }  
  inner_product_param {  
    num_output: 5  
    weight_filler {  
      type: "xavier"  
      std: 0.005  
    }  
    bias_filler {  
      type: "constant"  
      value: 0.1  
    }  
  }  
}  

layer {  
  bottom: "fc8"  
  bottom: "Headposes"  
  top: "headposeloss1"  
  name: "headposeloss1"  
  type: "SoftmaxWithLoss"  
}

solver.prototxt:

train_net: "ZOO_VGG16/train2.prototxt"
base_lr: 0.01
display: 20
max_iter: 100000
lr_policy: "step"
gamma: 0.1
momentum: 0.9
weight_decay: 0.0005
stepsize: 50000
snapshot: 5000
snapshot_prefix: "snapshots_pointing04_vgg16_klLoss/cross1/vgg_"
random_seed: 831486
iter_size: 1

参考文献：

  1. https://github.com/NVIDIA/DIGITS/issues/159#issuecomment-247707549
  2. https://github.com/NVIDIA/DIGITS/issues/535
  3. https://stackoverflow.com/questions/42652903/caffe-net-not-converging-when-replacing-alexnet-with-vgg16-but-everything-else?rq=1
  4. https://github.com/BVLC/caffe/wiki/Model-Zoo
  5. https://www.cnblogs.com/ryans/p/8196151.html
机器学习的小学生
关注
  • 3
    点赞
  • 踩
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
matlab导入vgg16,简单导入VGG16
weixin_30899023的博客
03-20 2323
走了几个坑把VGG16导入到模型中，在此记录下代码，以备不时之需。代码运行所需文件：vgg_16.ckpt1.jpg (224 x 224 x 3)import tensorflow as tffrom tensorflow.python import pywrap_tensorflowvgg16_ckpt_path = 'vgg_16.ckpt'def load_model(input,mode...
vgg16 清华镜像_Python models.vgg16方法代码示例
weixin_33264203的博客
12-31 2327
本文整理汇总了Python中torchvision.models.vgg16方法的典型用法代码示例。如果您正苦于以下问题：Python models.vgg16方法的具体用法？Python models.vgg16怎么用？Python models.vgg16使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在模块torchvision.models的...
vgg16
kui9702的博客
12-30 1738
引言 ​ ⽜津⼤学的视觉⼏何组（visualgeometry group）92的VGG⽹络,采用块状结构，为后续的神经网络提供模板。 ​ 与AlexNet、LeNet⼀样，VGG⽹络可以分为两部分：第⼀部分主要由卷积层和汇聚层组成，第⼆部分由全连接层组成。 ​ 本节 我们走进vgg16 VGG Net原论文 https://blog.csdn.net/Jwenxue/article/details/89207067 实际上我们在使用较多的vgg16，是属于上图D。 整理之后的网络
基于Pytorch框架构建VGG-16模型
最新发布
2301_78972534的博客
06-25 715
前向传播函数接收输入x，首先通过特征提取部分self.features，然后将特征图展开为一维向量，最后通过分类器部分self.classifier得到最终的分类结果
Vgg16
devilangel2的博客
02-16 618
VGG： VGG卷积神经网络是牛津大学在2014年提出来的模型。当这个模型被提出时，由于它的简洁性和实用性，马上成为了当时最流行的卷积神经网络模型。它在图像分类和目标检测任务中都表现出非常好的结果。在2014年的ILSVRC比赛中，VGG 在Top-5中取得了92.3%的正确率。该模型有一些变种，其中最受欢迎的当然是 vgg-16，这是一个拥有16层的模型。你可以看到它需要维度是 224*22...
Pytorch构建vgg16模型
2401_83576060的博客
06-17 1012
Block 1# Block 2# Block 3# Block 4# Block 5nn.Linear(4096, num_classes) # 修改这里，默认为1000个类别x = torch.flatten(x, 1) # 展开特征图return x注：这段代码定义了一个继承自nn.Module的类VGG16，它是一个用于图像分类的卷积神经网络模型。：定义了一个名为VGG16的类，它继承自nn.Module，这是PyTorch中定义神经网络模型的基础类。definit。
VGG16神经网络搭建
2301_78820199的博客
03-26 913
VGG神经网络的模型搭建！思路清晰，代码详解！
深度学习——VGG16模型详解
热门推荐
橙子的博客
03-02 9万+
1、网络结构 VGG16模型很好的适用于分类和定位任务，其名称来自牛津大学几何组（Visual Geometry Group）的缩写。 根据卷积核的大小核卷积层数，VGG共有6种配置，分别为A、A-LRN、B、C、D、E，其中D和E两种是最为常用的VGG16和VGG19。 介绍结构图： conv3-64 ：是指第三层卷积后维度变成64，同样地，conv3-128指的是第三层卷积后维度变成128； input（224x224 RGB image） ：指的是输入图片大小为224244的彩色图像，通道为
VGG16结构图
Activewaste
09-02 1133
vgg16构造模型图：http://ethereon.github.io/netscope/#/gist/dc5003de6943ea5a6b8b softmax层一般连接的是全连接层和loss层，现在的CNN都是end-to-end的，最后通过全连接层送入softmax来进行分类。 ...
Pytorch之VGG16图像分类
风间琉璃的博客
09-26 4290
VGG是Oxford的VisualGeometryGroup的组提出的。该网络是在ILSVRC 2014上的相关工作，主要工作是证明了增加网络的深度能够在一定程度上影响网络最终的性能。斩获该年ImageNet竞赛中Localization Task（定位任务）第一名和Classification Task（分类任务）第二名。
vgg16_VGG16_
10-01
VGG16是一种深度卷积神经网络（Convolutional Neural Network, CNN）模型，由英国牛津大学的Visual Geometry Group（VGG）在2014年的ImageNet竞赛中提出。该模型以其深而窄的架构闻名，拥有16个处理层，其中13层是卷...
Vgg16 model
03-25
vgg16 模型 用于初始训练，准确率非常高，可以直接将其封装到云平台中！
vgg16_weights.zip
07-07
VGG16是一种深度卷积神经网络（Convolutional Neural Network, CNN），由英国的Visual Geometry Group在2014年的ImageNet Large Scale Visual Recognition Challenge（ILSVRC）上提出。该模型以其深架构和相对简单的...
VGG16_vgg16代码_VGG16_vgg16代码详解_
09-29
VGG16是一种深度卷积神经网络（Deep Convolutional Neural Network, DCNN），由英国牛津大学的Visual Geometry Group（VGG）在2014年的ImageNet竞赛中提出。该模型以其深且窄的架构闻名，拥有16个处理层，其中13层是...
vgg16-397923af.pth
08-17
VGG16是一个著名的卷积神经网络（CNN）模型，由英国剑桥大学的Visual Geometry Group（VGG）在2014年的ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 中提出。这个模型因其深度和准确性而备受关注，...
Caffe Scale层
机器学习的小学生
05-08 1万+
如果我们想原封不动的传送数据，也就是说建一个不做任何操作仅穿数据的层，可以利用Scale层，Python中写法如下： n.scale1 = L.Scale(n.pool2,name='scale1',param=dict(lr_mult=0),filler=dict(type="constant",value=1)) 生成的prototxt协议文件如下： layer { name:...
Win7 安装 VS 2015 运行C++时提示ucrtbased.dll丢失 的解决方法
机器学习的小学生
09-06 1万+
This problem is from VS 2015 silently failing to copy ucrtbased.dll (debug) and ucrtbase.dll (release) into the appropriate system folders during the installation of Visual Studio. (Or you did not sele
caffe 自定义层/添加自己的损失函数
机器学习的小学生
03-12 9621
自定义激活层文献[2] 以循序渐进的学习方式先后介绍了： google protocol buffe , Blob ,SyncedMemory ,shared_ptr ,layer,data layer 然后利用这些知识来自定义一个层。其给出的例子是定义一个power层，可以通过caffe的api参考其结构：http://caffe.berkeleyvision.org/doxygen/cla
pytorch vgg16
09-05
PyTorch提供了vgg16模型的预训练版本，可以用于图像分类任务。你可以使用`torchvision.models`模块来加载vgg16模型。下面是一个简单的示例代码: ```python import torch import torchvision.models as models # ...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
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
实付元
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