VGG_19 train_vali.prototxt file
name: "VGG_ILSVRC_19_layer" layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
image_data_param {
batch_size: 12
source: "../../fine_tuning_data/HAT_fineTuning_data/train_data_fineTuning.txt"
root_folder: "../../fine_tuning_data/HAT_fineTuning_data/train_data/"
}
} layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
}
image_data_param {
batch_size: 10
source: "../../fine_tuning_data/HAT_fineTuning_data/test_data_fineTuning.txt"
root_folder: "../../fine_tuning_data/HAT_fineTuning_data/test_data/"
}
} layer {
bottom:"data"
top:"conv1_1"
name:"conv1_1"
type:"Convolution"
convolution_param {
num_output:64
pad:1
kernel_size:3
}
}
layer {
bottom:"conv1_1"
top:"conv1_1"
name:"relu1_1"
type:"ReLU"
}
layer {
bottom:"conv1_1"
top:"conv1_2"
name:"conv1_2"
type:"Convolution"
convolution_param {
num_output:64
pad:1
kernel_size:3
}
}
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"
convolution_param {
num_output:128
pad:1
kernel_size:3
}
}
layer {
bottom:"conv2_1"
top:"conv2_1"
name:"relu2_1"
type:"ReLU"
}
layer {
bottom:"conv2_1"
top:"conv2_2"
name:"conv2_2"
type:"Convolution"
convolution_param {
num_output:128
pad:1
kernel_size:3
}
}
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"
convolution_param {
num_output:256
pad:1
kernel_size:3
}
}
layer {
bottom:"conv3_1"
top:"conv3_1"
name:"relu3_1"
type:"ReLU"
}
layer {
bottom:"conv3_1"
top:"conv3_2"
name:"conv3_2"
type:"Convolution"
convolution_param {
num_output:256
pad:1
kernel_size:3
}
}
layer {
bottom:"conv3_2"
top:"conv3_2"
name:"relu3_2"
type:"ReLU"
}
layer {
bottom:"conv3_2"
top:"conv3_3"
name:"conv3_3"
type:"Convolution"
convolution_param {
num_output:256
pad:1
kernel_size:3
}
}
layer {
bottom:"conv3_3"
top:"conv3_3"
name:"relu3_3"
type:"ReLU"
}
layer {
bottom:"conv3_3"
top:"conv3_4"
name:"conv3_4"
type:"Convolution"
convolution_param {
num_output:256
pad:1
kernel_size:3
}
}
layer {
bottom:"conv3_4"
top:"conv3_4"
name:"relu3_4"
type:"ReLU"
}
layer {
bottom:"conv3_4"
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"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv4_1"
top:"conv4_1"
name:"relu4_1"
type:"ReLU"
}
layer {
bottom:"conv4_1"
top:"conv4_2"
name:"conv4_2"
type:"Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv4_2"
top:"conv4_2"
name:"relu4_2"
type:"ReLU"
}
layer {
bottom:"conv4_2"
top:"conv4_3"
name:"conv4_3"
type:"Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv4_3"
top:"conv4_3"
name:"relu4_3"
type:"ReLU"
}
layer {
bottom:"conv4_3"
top:"conv4_4"
name:"conv4_4"
type:"Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv4_4"
top:"conv4_4"
name:"relu4_4"
type:"ReLU"
}
layer {
bottom:"conv4_4"
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"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv5_1"
top:"conv5_1"
name:"relu5_1"
type:"ReLU"
}
layer {
bottom:"conv5_1"
top:"conv5_2"
name:"conv5_2"
type:"Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv5_2"
top:"conv5_2"
name:"relu5_2"
type:"ReLU"
}
layer {
bottom:"conv5_2"
top:"conv5_3"
name:"conv5_3"
type:"Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv5_3"
top:"conv5_3"
name:"relu5_3"
type:"ReLU"
}
layer {
bottom:"conv5_3"
top:"conv5_4"
name:"conv5_4"
type:"Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom:"conv5_4"
top:"conv5_4"
name:"relu5_4"
type:"ReLU"
}
layer {
bottom:"conv5_4"
top:"pool5"
name:"pool5"
type:"Pooling"
pooling_param {
pool:MAX
kernel_size: 2
stride: 2
}
}
layer {
bottom:"pool5"
top:"fc6_"
name:"fc6_"
type:"InnerProduct"
inner_product_param {
num_output: 4096
}
}
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"
inner_product_param {
num_output: 4096
}
}
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"
inner_product_param {
num_output: 27
}
} layer {
name: "sigmoid"
type: "Sigmoid"
bottom: "fc8_"
top: "fc8_"
} layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8_"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
} layer {
name: "loss"
type: "EuclideanLoss"
bottom: "fc8_"
bottom: "label"
top: "loss"
}
VGG_19 train_vali.prototxt file的更多相关文章
- 如何才能将Faster R-CNN训练起来?
如何才能将Faster R-CNN训练起来? 首先进入 Faster RCNN 的官网啦,即:https://github.com/rbgirshick/py-faster-rcnn#installa ...
- SSD框架训练自己的数据集
SSD demo中详细介绍了如何在VOC数据集上使用SSD进行物体检测的训练和验证.本文介绍如何使用SSD实现对自己数据集的训练和验证过程,内容包括: 1 数据集的标注2 数据集的转换3 使用SSD如 ...
- Faster-RCNN 训练自己的数据
在前一篇随笔中,数据制作成了VOC2007格式,可以用于Faster-RCNN的训练. 1.针对数据的修改 修改datasets\VOCdevkit2007\VOCcode\VOCinit.m,我只做 ...
- caffe drawnet.py 用Python画网络框架
在caffe中可以使用draw_net.py轻松地绘制卷积神经网络(CNN,Convolutional Neural Networks)的架构图.这个工具对于我们理解.学习甚至查错都有很大的帮助. 1 ...
- caffe实际运行中遇到的问题
https://blog.csdn.net/u010417185/article/details/52649178 1.均值计算是否需要统一图像的尺寸? 在图像计算均值时,应该先统一图像的尺寸,否则会 ...
- [OpenCV] Install OpenCV 3.3 with DNN
OpenCV 3.3 Aug 3, 2017 OpenCV 3.3 has been released with greatly improved Deep Learning module and l ...
- [PyImageSearch] Ubuntu16.04 使用深度学习和OpenCV实现物体检测
上一篇博文中讲到如何用OpenCV实现物体分类,但是接下来这篇博文将会告诉你图片中物体的位置具体在哪里. 我们将会知道如何使用OpenCV‘s的dnn模块去加载一个预训练的物体检测网络,它能使得我们将 ...
- 【PyImageSearch】Ubuntu16.04使用OpenCV3.3.0实现图像分类
这篇博文将会展示如何采用一个预训练的深度学习网络(模型)在ImageNet的数据集并把它当作输入图像. 首先说明,运行环境为Ubuntu16.04(或者MacOS),windows暂不支持,已经编译好 ...
- 机器学习进阶-目标追踪-SSD多进程执行 1.cv2.dnn.readnetFromCaffe(用于读取已经训练好的caffe模型) 2.delib.correlation_tracker(生成追踪器) 5.cv2.writer(将图片写入视频中) 6.cv2.dnn.blobFromImage(图片归一化) 10.multiprocessing.process(生成进程)
1. cv2.dnn.readNetFromCaffe(prototxt, model) 用于进行SSD网络的caffe框架的加载 参数说明:prototxt表示caffe网络的结构文本,model ...
随机推荐
- C++ primer的第一章的主要内容
第一章主要是把C++的主要的部分简单的介绍了一下,让读者对C++开始有一个简单的了解.看完第一章的收获就是知道如何去读入不确定数目的输入,主要是形式是:whlie(cin>>s){},利用 ...
- 2013年7月份第3周51Aspx源码发布详情
批量重命名文件工具源码 2013-7-19 [VS2010]功能介绍:这是一个新型的文件重命名,主要用了TreeView(树形视图)来选择文件夹,批量进行文件重命名.其中,有"编号在前,编 ...
- hdu 2071
Ps:输出n个数里最大的 #include "stdio.h" int main(){ ],max; int i,j,n,t; while(~scanf("%d" ...
- HDU 4349 Xiao Ming's Hope
有这样一个性质:C(n,m)%p=C(p1,q1)*C(p2,q2).......%p,其中pkpk-1...p1,qkqk-1...q1分别是n,m在p进制下的组成. 就完了. #include&l ...
- Unity3D入门(一):环境搭建
1.Unity3D 目前最新正式版本是4.2.1f 官网下载,以前的版本安装时候需要序列号激活,新版本4.2.1f 不需要,完全免费,但发布的时候需要许可证 2.要学习的同学,下载频道可以找到破解补 ...
- Fish入门
安装以及配置 Linux和OS X基本都可以通过源来安装,实在不行就下载源码编译,不难的. 安装好第一步是修改OS默认shell: chsh -s /usr/bin/fish 然后就可以直接使用了,就 ...
- flex+java实现文件的上传
flex前端代码: <?xml version="1.0" encoding="utf-8"?><s:BorderContainer xmln ...
- 转:DataTable.Compute()用法
转自:http://www.cnblogs.com/fanyf/archive/2012/05/11/2495919.html一.DataTable.Compute()方法說明如下 作用: 计算用来传 ...
- 有趣的数-回文数(Palindrome number)
文章转自http://blog.163.com/hljmdjlln@126/blog/static/5473620620120412525181/ 做LC上的题"Palindrome num ...
- 机器学习技法-决策树和CART分类回归树构建算法
课程地址:https://class.coursera.org/ntumltwo-002/lecture 重要!重要!重要~ 一.决策树(Decision Tree).口袋(Bagging),自适应增 ...