Hi_Panda

只有坚持不懈的努力,才可以做自己喜欢的事。

Caffe GNU error

*** Aborted at 1491880114 (unix time) try "date -d @1491880114" if you are using GNU date *** PC: @ 0x7fefd5f82cde (unknown) *** SIGSEG...

2017-04-11 11:11:35

阅读数 657

评论数 2

Caffe Layer Library

Convolution layer# convolution layer { name: "loss1/conv" type: "Convolution" bottom: "loss1/ave_pool" top: &qu...

2017-03-14 15:22:33

阅读数 3366

评论数 1

Caffe Log Visualization

1.Record your train/test log as a log fileTOOLS=./build/tools GLOG_logtostderr=0 GLOG_log_dir=deepid/deepid2/Log/ \ $TOOLS/caffe train \ --so...

2016-09-28 14:28:41

阅读数 734

评论数 0

Caffe --- SyncedMemory

SyncedMemory类定义在syncedmem.hpp/cpp里, 主要负责caffe底层的内存管理.PS: Caffe的底层数据的切换(cpu模式和gpu模式),需要用到内存同步模块。其实个人觉得如果需要研究Blob,对于SyncedMemory的分析很重要内存分配与释放内存分配与释放由两个...

2016-07-25 09:59:49

阅读数 482

评论数 0

Caffe --- blob code

两篇非常好的文章: http://blog.csdn.net/xizero00/article/details/50886829# http://www.cnblogs.com/yymn/articles/5341347.html

2016-07-23 13:02:21

阅读数 382

评论数 0

Caffe Solver

Solver scaffolds the optimization bookkeeping and creates the training network for learning and test network(s) for evaluation. iteratively op...

2016-07-21 15:46:39

阅读数 361

评论数 0

Blobs, Layers, and Nets: anatomy of a Caffe model

BlobsBlob作为Caffe的四大模块之一,负责完成CPU/GPU存储申请、同步和数据持久化映射。Caffe内部数据存储和通讯都是通过Blob来完成,Blob提供统一的存储操作接口,可用来保存训练数据、模型参数等。Blob 事实上是调用了SyncedMemory 类。SyncedMemory类...

2016-07-21 15:39:26

阅读数 695

评论数 0

deeplab script---python

import os,sys, subprocess sys.path.insert(0, os.getcwd()+'/python/my_script/') from tester import tester from trainer import trainer from crf_runne...

2016-06-01 07:53:21

阅读数 1343

评论数 0

deepLab

1.matio can't find HDF5 libraries change file /densecrf/makefile as: g++ refine_pascal_v4/dense_inference.cpp util/Timer.h libDenseCRF.a $(CC) refi...

2016-05-30 07:20:29

阅读数 2897

评论数 0

Caffe重新编译

从github获得的很多caffe源码都需要重新编译: 流程: 1、Makefile.config文件(cudnn、) 2、修改Makefile文件(Open cv和MKL) 修改mkl的路径 添加opencv包含库 3、$ rm -rf ./build/* 清除build $ make a...

2016-05-20 18:03:22

阅读数 3235

评论数 1

Caffe专业术语

Blob: the blob is the standard array and unified memory interface for the framework. The details of blob describe how information is stored and commu...

2016-04-14 08:38:55

阅读数 451

评论数 0

bin to npy

import caffe % suppose caffe is already in the path of Python import numpy as np import sys blob = caffe.proto.caffe_pb2.BlobProto() data = open( 'd...

2016-04-09 11:35:23

阅读数 356

评论数 0

Caffe-Caffe Models

1.bvlc_reference_caffenet.caffemodel 下载地址:http://dl.caffe.berkeleyvision.org/bvlc_reference_caffenet.caffemodel 来源:caffe中ImageNet tutorial(Brew Imag...

2016-03-14 08:41:51

阅读数 704

评论数 0

Caffe Examples

1.ImageNet tutorial Train and test "CaffeNet" on ImageNet data.

2016-03-14 08:34:34

阅读数 2041

评论数 2

使用Python中draw_net.py画网络结构图

python python/draw_net.py /home/vr/Documents/Caffe/setup/caffe-master/examples/mnist/lenet.prototxt /home/vr/Documents/Caffe/setup/caffe-master/examp...

2016-03-12 12:19:50

阅读数 3763

评论数 0

Train and Test LeNet on your own dataset

This post walk you through how to train LeNet (defined in examples/mnist/lenet.prototxt) using your own dataset( jpg images of the same size or prep...

2016-03-12 10:43:15

阅读数 837

评论数 0

LeNet: the MNIST Classification Model

name: "LeNet" layer { name: "mnist" type: "Data" top: "data" top: "label" include { p...

2016-03-05 10:28:42

阅读数 965

评论数 0

Caffe安装问题汇总

1.cannot open shared object file no such file or directory runtest error 127 caffe export LD_LIBRARY_PATH=/usr/local/cuda-6.5/lib64:$LD_LIBRARY_PATHl...

2016-03-05 09:39:46

阅读数 3577

评论数 0

Caffe

1、下载: 在官网(https://developer.nvidia.com/cudnn)下载,但是需要注册 或者,在http://pan.baidu.com/s/1dDsD7XZ(密码:eqsz)下载,但是不保证是最新版 2、安装: $ tar -xzvf cudnn-7.0-linux-x6...

2016-03-04 20:46:44

阅读数 278

评论数 0

caffe make runtest error(core dumped)Check failed: status == CUDNN_STATUS_SUCCESS (6 vs. 0)

参考了谷歌论坛 ================================================================= 简单讲就是GPU的加速性能不够,CUDNN只支持CUDA Capability 3.0以上的GPU加速 ==============...

2015-06-04 15:02:22

阅读数 3201

评论数 1

提示
确定要删除当前文章?
取消 删除
关闭
关闭