VGG-16 prototxt

最新推荐文章于 2024-04-27 00:02:47 发布
最新推荐文章于 2024-04-27 00:02:47 发布
阅读量1.7w 收藏 10
点赞数 6
分类专栏： caffe CNN 文章标签： CNN 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/baidu_24281959/article/details/52723666
版权
CNN 同时被 2 个专栏收录
33 篇文章 0 订阅
订阅专栏
caffe
17 篇文章 0 订阅
订阅专栏

solver.prototxt:

net: "models/vgg16/train_val.prototxt"
test_iter: 1000
test_interval: 2500
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 50000
display: 20
max_iter: 200000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "models/vgg16/caffe_vgg16_train"
solver_mode: GPU
train_val.prototxt: 
name: "VGG16"
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  # transform_param {
  #   mirror: true
  #   crop_size: 224
  #   mean_file: "data/ilsvrc12_shrt_256/imagenet_mean.binaryproto"
  # }
  transform_param {
    mirror: true
    crop_size: 224
    mean_value: 103.939
    mean_value: 116.779
    mean_value: 123.68
  }
  data_param {
    source: "data/ilsvrc12_shrt_256/ilsvrc12_train_leveldb"
    batch_size: 64
    backend: LEVELDB
  }
}
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  # transform_param {
  #   mirror: false
  #   crop_size: 224
  #   mean_file: "data/ilsvrc12_shrt_256/imagenet_mean.binaryproto"
  # }
  transform_param {
    mirror: false
    crop_size: 224
    mean_value: 103.939
    mean_value: 116.779
    mean_value: 123.68
  }
  data_param {
    source: "data/ilsvrc12_shrt_256/ilsvrc12_val_leveldb"
    batch_size: 50
    backend: LEVELDB
  }
}
layer {
  bottom: "data"
  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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: "gaussian"
      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: 1000
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0.1
    }
  }
}
layer {
  name: "accuracy_at_1"
  type: "Accuracy"
  bottom: "fc8"
  bottom: "label"
  top: "accuracy_at_1"
  accuracy_param {
    top_k: 1
  }
  include {
    phase: TEST
  }
}
layer {
  name: "accuracy_at_5"
  type: "Accuracy"
  bottom: "fc8"
  bottom: "label"
  top: "accuracy_at_5"
  accuracy_param {
    top_k: 5
  }
  include {
    phase: TEST
  }
}
layer {
  bottom: "fc8"
  bottom: "label"
  top: "loss"
  name: "loss"
  type: "SoftmaxWithLoss"
}



CodeCold
关注
  • 6
    点赞
  • 踩
  • 10
    收藏
    觉得还不错? 一键收藏
  • 26
    评论
专栏目录
caffe笔记: VGG16预训练模型微调
qiutian的博客
01-21 3042
在caffe里微调VGG-16用于自己的问题 以SnailTyan的预训练模型VGG-16为例，记录一些我这个小白最开始不能理解的概念 GitHub：https://github.com/SnailTyan/caffe-model-zoo/tree/master/VGG16 caffe相关概念： caffe里面的预训练模型就是一个网络在很大的数据集上训练得到的结果。.caffemodel文件里面...
vgg-face:使用pytorch加载vgg-face预训练的caffe模型
05-14
VGG网络通常包含16或19个卷积层，每个卷积层后面跟着一个池化层，最后是全连接层。在VGG-Face模型中，这种结构被优化以适应人脸特征的学习，使得模型能够有效地区分大量不同个体的脸部特征。 要使用PyTorch加载VGG-...
Caffe：如何运行一个pre-train过的神经网络——以VGG16为例
Lucifer_zzq的博客
07-21 4788
实验环境： Ubuntu 14.04 所需环境： Caffe（GPU） Python2.7 JUPYTER NOTEBOOK 所需依赖包： numpy matplotlib skimage h5py 本次实验采用的网络介绍： 在ICIR论文《VERY DEEP CONVOLUTIONAL NETWORK SFOR LARGE-SCALE IMAGE RECOGNITION》...
vgg16提取图片特征向量
vive921的博客
04-27 224
提取图片特征向量
Caffe实践 - 基于VGG16 多标签分类的训练与部署
长风破浪会有时，直挂云帆济沧海
08-25 4870
基于Caffe VGG16 的多标签分类 这里采用从图像直接读取图片数据和标签的方式进行多标签分类. 1. 问题描述 假定每张图片具有 N 个标签(本文N=3)，分别为 label1,label2,label3,...,labelNlabel1,label2,label3,...,labelN{label1, label2, label3,...,labelN}. 数据集 tr...
caffe入门 从vgg16结构学习caffe
有梦想的蜗牛
05-10 3779
name: "VGG_VOC0712_SSD_300x300_deploy" input: "data" input_shape { dim: 1 dim: 3 dim: 300 dim: 300 } layer { name: "conv1_1" type: "Convolution" bottom: "data" top: "conv1_1" param {
VGG网络讲解——小白也能懂
m0_57011726的博客
03-10 1万+
我们上文已经说了，VGG其实就是五层卷积。我们来看这个图：这个图是作者当时六次实验的结果图。在介绍这个图前，我先进行几个概念说明：卷积层全部为3*3的卷积核，用conv3-xxx来表示，xxx表示通道数。在这个表格中，我们可以看到，第一组（A）就是个简单的卷积神经网络，没有啥花里胡哨的地方。第二组（A-LRN）在第一组的卷积神经网络的基础上加了LRN（小白们不用太过了解这个，现在已经不是主流了，LRN是Alexnet中提出的方法，在Alexnet中有不错的表现 ）
vgg 16 和19 的 prototxt
05-04
在本文中，我们将深入探讨VGG16和VGG19的结构、工作原理以及如何通过`prototxt`文件进行可视化。 **VGG架构的核心特点** VGG模型的主要特点是它们的深层数量。VGG16拥有16个权重层，而VGG19则有19个。这两个模型都...
tensorflow-vgg16
10-09
TensorFlow VGG16是一个深度学习框架TensorFlow中的预训练模型，它基于VGG16网络架构。VGG16是由牛津大学视觉几何组（Visual Geometry Group）在2014年的ImageNet Large Scale Visual Recognition Challenge (ILSVRC...
VGG_ILSVRC_16_layers_deploy.prototxt
10-12
caffe训练 fcn需要的vgg VGG_ILSVRC_16_layers_deploy
opencv4.9.0+contrib-3rdparty ffmpeg、ippicv boostdesc、vgg-gener下载
最新发布
05-25
win10 opencv4.9.0 + contrib 编译安装 ffmpeg ippicv boostdesc vgg_generated 下载失败及 setlocal 错误解决（附文件下载） 1.opencv4.9.0_3rd.zip 解压到 opencv-4.9.0/build/3rdparty ffmpeg/ ffmpeg_version....
deploy.prototxt
04-27
python caffe中需要的文件models/bvlc_reference_caffenet/deploy.prototxt
Caffe学习系列(5)：其它常用层及参数
weixin_34376562的博客
12-24 244
本文讲解一些其它的常用层，包括：softmax_loss层，Inner Product层，accuracy层，reshape层和dropout层及其它们的参数配置。 1、softmax-loss softmax-loss层和softmax层计算大致是相同的。softmax是一个分类器，计算的是类别的概率（Likelihood），是Logistic Regression 的一种推广。Logist...
VGG 16 prototxt
请叫我小皇帝 的博客
05-10 3028
solver.prototxt: [cpp] view plain copy  print? net: "models/vgg16/train_val.prototxt"   test_iter: 1000   test_interval: 2500   base_lr: 0.001   lr_policy: "step"   gamma: 0.
fast-rcnn配置运行VGG16.caffemodel和VGG_CNN_M_1024.v2.caffemodel（Ubuntu14.04）
热门推荐
samylee的博客
03-27 1万+
在我的上个博客中已经对fast-rcnn配置运行demo.py做出了相应说明，在本博客中我将对fast-rcnn配置运行VGG16.caffemodel和VGG_CNN_M_1024.v2.caffemodel做出具体操作说明，希望可以解决大家在训练vgg网络时出现的问题。如果有训练不成功的朋友可以和我联系，邮箱ahuljx@126.com 好了，我们来玩玩这个fast-rcnn配置运行VGG16.caffemodel和VGG_CNN_M_1024.v2.caffemodel
[vgg16]vgg16相关文件
Jinming Su
08-03 1714
solver.prototxt net: "models/vgg16/train_val.prototxt" test_iter: 1000 test_interval: 2500 base_lr: 0.001 lr_policy: "step" gamma: 0.1 stepsize: 50000 display: 20 max_iter: 200000 ...
将tensorflow下训练的参数转化为caffemodel
zhaoyoulin2016的博客
07-31 3645
参考文档：http://www.cnblogs.com/unclelin/p/6984436.html                    https://blog.csdn.net/yiweibian/article/details/77185167 1、下载tensorflow2caffe源码：  地址：https://github.com/abner2015/tensorflow2c...
vgg-16猫狗识别
08-30
VGG-16是一种卷积神经网络模型，用于图像识别任务。猫狗识别是指利用计算机视觉技术对图像中的猫和狗进行分类和识别的任务。 VGG-16模型是由牛津大学的研究团队于2014年提出的。该模型的名称VGG是VGGNet的缩写，...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 26
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