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"}

时间： 2024-10-26 20:58:47

VGG_19 train_vali.prototxt file的相关文章

TRANSFORMING IMAGES TO FEATURE VECTORS

TRANSFORMING IMAGES TO FEATURE VECTORS I’m keen to explore some challenges in multimodal learning, such as jointly learning visual and textual semantics. However, I would rather not start by attempting to train an image recognition system from scratc

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如何训练4 使用SSD如何测试 1 数据集的标注数据的标注使用BBox-Label-Tool工具,该工具使用python实现,使用简单方便.该工具生成的标签格式是:object_numberx1min y1min x1max y1maxx2min y2min x2max y2max...2 数据集的

Python模块学习系列（8）----argparse模块

boost库很好的支持C++的命令行解析,能使我们的程序用起来更酷.最近一直想Python里也用上命令行,这样就不用再IDE里修改输入参数了.记得前面介绍过使用os模块也能解析命令行,但是那个比较简单,今天我们介绍的argparse模块是python中专门用来解析命令行的. 首先给大家贴出一段代码及运行结果,让大家有一个直观的感受. <span style="font-size:18px;">#!/usr/bin/env python """

Caffe---Pycaffe进行网络结构(xxx.prototxt)可视化

Pycaffe---进行网络结构(xxx.prototxt)可视化解决网络结构(xxx.prototxt)可视化,还可以借助python接口,编写一个类似如下的pycaffe_draw_net.py: # -*- coding: utf-8 -*- #!/usr/bin/env python import caffe import caffe.draw from caffe.proto import caffe_pb2 from google.protobuf import text_form

JavaSE8基础 File lastModified 获取文件夹的修改日期

os :windows7 x64 jdk:jdk-8u131-windows-x64 ide:Eclipse Oxygen Release (4.7.0) information: 通过这张截图可以看到测试文件夹的修改日期. code: package jizuiku0; import java.io.File; import java.text.SimpleDateFormat; import java.util.Date; /* * @version V17.09 */ pu

JavaSE8基础 File createNewFile 在一个不存在的文件夹中创建文件时会抛IO异常(绝对路径)

os :windows7 x64 jdk:jdk-8u131-windows-x64 ide:Eclipse Oxygen Release (4.7.0) information: 在编写代码时,javase8文件夹的情况截图. code: package jizuiku0; import java.io.File; import java.io.IOException; /* * @version V17.09 */ public class FileDemo_1 { public

JavaSE8基础 File getAbsolutePath 获取当前默认的工作文件夹路径

os :windows7 x64 jdk:jdk-8u131-windows-x64 ide:Eclipse Oxygen Release (4.7.0) code: package jizuiku0; import java.io.File; /* * @version V17.09 */ public class GetDemo { public static void main(String[] args) { System.out.println("当前的默认工作路径是:&q

JavaSE8基础 File FilenameFilter 筛选出指定后缀名的文件

os :windows7 x64 jdk:jdk-8u131-windows-x64 ide:Eclipse Oxygen Release (4.7.0) code: package jizuiku0; import java.io.File; import java.io.FilenameFilter; /* * @version V17.09 */ public class Filter { public static void main(String[] args) { //

JavaSE8基础 File list 获取指定文件夹下的第一层文件和文件夹的名字

os :windows7 x64 jdk:jdk-8u131-windows-x64 ide:Eclipse Oxygen Release (4.7.0) information: 被查看文件夹中的内容截图. code: package jizuiku0; import java.io.File; /* * @version V17.09 */ public class GetName { public static void main(String[] args) { String