caffe Python API 之激活函数ReLU
import sys
import os
sys.path.append("/projects/caffe-ssd/python")
import caffe net = caffe.NetSpec()
net.data, net.label = caffe.layers.Data(
name="InputData",
source="train_lmdb",
backend = caffe.params.Data.LMDB,
batch_size=32,
ntop=2,
include=dict(phase=caffe.TRAIN),
transform_param=dict(
crop_size=227,
mean_value=[104, 117, 123],
mirror=True
)
)
net.myconv = caffe.layers.Convolution(
net.data,
kernel_size=3,
stride=1,
pad=1,
num_output=20,
group=2,
weight_filler=dict(type='xavier'),
bias_filler=dict(type='constant',value=0)) net.myrelu = caffe.layers.ReLU(net.myconv, in_place=True) print(str(net.to_proto())) 输出:
layer {
name: "InputData"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 227
mean_value: 104.0
mean_value: 117.0
mean_value: 123.0
}
data_param {
source: "train_lmdb"
batch_size: 32
backend: LMDB
}
}
layer {
name: "myconv"
type: "Convolution"
bottom: "data"
top: "myconv"
convolution_param {
num_output: 20
pad: 1
kernel_size: 3
group: 2
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "myrelu"
type: "ReLU"
bottom: "myconv"
top: "myconv"
}
caffe Python API 之激活函数ReLU的更多相关文章
- caffe Python API 之中值转换
# 编写一个函数,将二进制的均值转换为python的均值 def convert_mean(binMean,npyMean): blob = caffe.proto.caffe_pb2.BlobPro ...
- caffe Python API 之 数据输入层(Data,ImageData,HDF5Data)
import sys sys.path.append('/projects/caffe-ssd/python') import caffe4 net = caffe.NetSpec() 一.Image ...
- caffe Python API 之BatchNormal
net.bn = caffe.layers.BatchNorm( net.conv1, batch_norm_param=dict( moving_average_fraction=0.90, #滑动 ...
- caffe Python API 之上卷积层(Deconvolution)
对于convolution: output = (input + 2 * p - k) / s + 1; 对于deconvolution: output = (input - 1) * s + k ...
- caffe Python API 之可视化
一.显示各层 # params显示:layer名,w,b for layer_name, param in net.params.items(): print layer_name + '\t' + ...
- caffe Python API 之Inference
#以SSD的检测测试为例 def detetion(image_dir,weight,deploy,resolution=300): caffe.set_mode_gpu() net = caffe. ...
- caffe Python API 之图片预处理
# 设定图片的shape格式为网络data层格式 transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape}) ...
- caffe Python API 之Model训练
# 训练设置 # 使用GPU caffe.set_device(gpu_id) # 若不设置,默认为0 caffe.set_mode_gpu() # 使用CPU caffe.set_mode_cpu( ...
- caffe Python API 之Solver定义
from caffe.proto import caffe_pb2 s = caffe_pb2.SolverParameter() path='/home/xxx/data/' solver_file ...
随机推荐
- winform全局异常捕获
/// <summary> /// 应用程序的主入口点. /// </summary> public static ApplicationContext context; [S ...
- P1825 [USACO11OPEN]玉米田迷宫Corn Maze
题目描述 This past fall, Farmer John took the cows to visit a corn maze. But this wasn't just any corn m ...
- [Leetcode] valid parentheses 有效括号对
Given a string containing just the characters'(',')','{','}','['and']', determine if the input strin ...
- github clone 指定的tag
git clone --branch [tags标签] [git地址] 使用branch参数,后面加上tag标签,最后是git仓库的地址
- 一种高效的寻路算法 - B*寻路算法
在此把这个算法称作B* 寻路算法(Branch Star 分支寻路算法,且与A*对应),本算法适用于游戏中怪物的自动寻路,其效率远远超过A*算法,经过测试,效率是普通A*算法的几十上百倍. 通过引入该 ...
- nfs挂载权限问题
问题: 服务器A:192.168.10.230 服务器B:192.168.10.231 由于服务器A空间不足,打算将服务器A产生的数据库日志挂载到服务器B上,刚开始设定的anonuid和anongid ...
- [10.12模拟赛] 老大 (二分/树的直径/树形dp)
[10.12模拟赛] 老大 题目描述 因为 OB 今年拿下 4 块金牌,学校赞助扩建劳模办公室为劳模办公室群,为了体现 OI 的特色,办公室群被设计成了树形(n 个点 n − 1 条边的无向连通图), ...
- ubuntu启动脚本
下午分析了一下mysql的启动脚本,找到这篇,记录一下,目前很多服务都是以这种方式封装,后面自己写来借鉴一下 http://blog.fens.me/linux-upstart/
- SpringMVC 用注解Annotation驱动的IoC功能@Autowired @Component
转载自:http://blog.csdn.net/lufeng20/article/details/7598564 本文分为三个部分:概述.使用注解进行属性注入.使用注解进行Bean的自动定义. 一, ...
- [LeetCode] Binary Tree Level Order Traversal 与 Binary Tree Zigzag Level Order Traversal,两种按层次遍历树的方式,分别两个队列,两个栈实现
Binary Tree Level Order Traversal Given a binary tree, return the level order traversal of its nodes ...