深度学习之解决问题2018.4.10

各种深度学习过程中遇到的问题:

从零开始~Ubuntu16.04安装caffe+cuda9.1+cndnn9.1+OpenCV2.4.9
http://blog.csdn.net/cpfelix/article/details/79086580

Ubuntu下如何安装TensorFlow(注意安装的为CPU版本,cuda9.1不兼容)
http://blog.csdn.net/tina_ttl/article/details/51762471 

ubuntu 14.04 搭建GPU深度学习 tensorflow 平台(18.3.12最新在cuda7.5安装成功,用sudo pip install --ignore-installed安装一直importerror) 
http://blog.csdn.net/myjiayan/article/details/52084662

Ubuntu环境下基于Anaconda安装Tensorflow
http://blog.csdn.net/hgdwdtt/article/details/78633232


Ubuntu下同时安装caffe和tensorflow
http://www.cnblogs.com/heubme/p/7850348.html

Ubuntu14.04 安装 CUDA-7.5(deb安装) +tensorflow
http://blog.csdn.net/zhongshaoyy/article/details/54575116

Faster R-CNN的安装、测试经历:
http://blog.csdn.net/wopawn/article/details/52751614

py-faster-rcnn用自己的数据训练模型:
http://blog.csdn.net/princepaul3/article/details/52313582

Ubuntu16.04环境下安装caffe及运行faster-rcnn
http://blog.csdn.net/zoro_lov3/article/details/60581174

pva-faster-rcnn配置安装及训练自己的数据集
http://blog.csdn.net/samylee/article/details/52860038


CharlesShang/FastMaskRCNN

https://github.com/CharlesShang/FastMaskRCNN

安装教程(一):使用Anaconda创建caffe和tensorflow共存环境 | Jack Cui
http://cuijiahua.com/blog/2017/12/dl_1.html

安装教程:使用Anaconda创建caffe和tensorflow共存环境
http://blog.csdn.net/primezpy/article/details/78819249

make: *** [.build_release/lib/libcaffe.so.1.0.0-rc3] Error 1
https://www.cnblogs.com/zjutzz/p/5716453.html?utm_source=itdadao&utm_medium=referral

如何在Anaconda的python和系统自带的python之间切换 
http://blog.csdn.net/teeyohuang/article/details/79076821

编译caffe的一个protobuf问题 (未采用)
http://blog.csdn.net/qq_17278169/article/details/64128525

安装教程:使用Anaconda创建caffe和tensorflow共存环境
http://blog.csdn.net/primezpy/article/details/78819249

KeyError: 'chair'
http://www.bubuko.com/infodetail-2096570.html


py-faster-rcnn】【训练自己数据】需要修改的参数小记

http://blog.csdn.net/amor_tila/article/details/78452261


Caffe Implementation of Google's MobileNets (v1 and v2) 
https://github.com/shicai/MobileNet-Caffe

faster rcnn测试VOC2012的问题
https://www.cnblogs.com/xthrough/p/6386651.html

训练GoogLeNet出现问题:check failed:mdb_status==0(2vs.0)No such file or directiry [
http://bbs.csdn.net/topics/391931961

MobileNet教程(2):用TensorFlow搭建安卓手机上的图像分类App
https://baijiahao.baidu.com/s?id=1574957535863211&wfr=spider&for=pc

TensorFlow 安装教程 
http://blog.csdn.net/bitcarmanlee/article/details/52749488

Tensorflow 跑MaskRCNN框架遇到的各种坑(一)
http://blog.csdn.net/aimer_chen/article/details/78528000

matterport Mask_RCNN配置
http://blog.csdn.net/wei_guo_xd/article/details/78579534

用自己的数据训练Faster-RCNN,tensorflow版本(二)
http://blog.csdn.net/lanyuelvyun/article/details/78094003

关于coco数据集的pycocotools/_mask.so: undefined symbol: _Py_ZeroStruct报错问题 
http://blog.csdn.net/ab0902cd/article/details/79085797


protobuf 3.1.0 安装示例和使用指南说明

http://blog.csdn.net/mircosheng/article/details/70141704

/autogen.sh: 4: autoreconf: not found
https://blog.csdn.net/ww506772362/article/details/42265381

protobuf的安装和卸载(主要)

http://blog.csdn.net/tuhuolong/article/details/78353519

linux下安装google protobuf(更改安装位置)

https://blog.csdn.net/xiexievv/article/details/47396725

protobuf 安装与使用

http://blog.csdn.net/csqingchen/article/details/50669725 

caffe训练出错:malloc(): memory corruption
http://blog.csdn.net/u011070171/article/details/52846306

Ubuntu16.04+CUDA9.1+cudnn-..-v7环境安装caffe runtest出现问题
http://blog.csdn.net/pzh16789/article/details/78913107

BatchReindexLayer fails GPU gradient tests under CUDA v9.1 #
https://github.com/BVLC/caffe/issues/6164

tensorflow tf.python_io模块源码阅读 
http://blog.csdn.net/fengwuxuan/article/details/77482404

Ubuntu + CUDA9.0 + tensorflow-gpu 安装过程
http://blog.csdn.net/qq_35976351/article/details/79325476

Anaconda环境下OpenCV的安装方法
http://blog.csdn.net/u011501388/article/details/76320974

ImportError: dlopen: cannot load any more object with static TLS
http://blog.csdn.net/u012609509/article/details/78432323

[Tensorflow]基于slim框架下inception模型的植物识别
http://blog.csdn.net/wlzard/article/details/77689311

FastRCNN 训练自己数据集 (1编译配置)
http://www.cnblogs.com/louyihang-loves-baiyan/p/4885659.html

fast-rcnn训练自己数据集以及demo代码解读和总结(面向fast-rcnn初学者) 
http://blog.csdn.net/u010668907/article/details/50991664

sergeyk/selective_search_ijcv_with_python
https://github.com/sergeyk/selective_search_ijcv_with_python

selective search生成.mat文件
https://www.cnblogs.com/ymjyqsx/p/6959328.html

python opencv入门 Hough圆变换(28) 
http://blog.csdn.net/tengfei461807914/article/details/77507820

facebookresearch/Detectron
https://github.com/facebookresearch/Detectron

caffe学习(七):使用py-faster-rcnn来训练voc2007数据集(Ubuntu) 
http://blog.csdn.net/hongbin_xu/article/details/77278329

faster rcnn报错:TypeError: slice indices must be integers or None or have an __index__ method
http://blog.csdn.net/qq_27637315/article/details/78849756

Python脚本运行出现语法错误:IndentationError:unexpected indent
https://www.cnblogs.com/gary-bao/p/5142102.html

Python图片裁剪实例代码(如头像裁剪)
http://www.jb51.net/article/116789.htm

TypeError: slice indices must be integers or None or have an __index__ method
https://www.jianshu.com/p/9137efc1bd8f

File "/home/scau2/Downloads/py-faster-rcnn/tools/../lib/datasets/voc_eval.py", line 148, in voc_eval
    BB = BB[sorted_ind, :]
IndexError: too many indices for array
https://blog.csdn.net/lhanchao/article/details/70807912

ImportError: numpy.core.multiarray failed to import
https://www.jianshu.com/p/9137efc1bd8f

源码安装tensorflow Cuda Configuration Error: Cannot find libdevice.10.bc under /usr/local/cuda-7.5
INFO: Elapsed time: 0.071s
FAILED: Build did NOT complete successfully (0 packages loaded)
    currently loading: tensorflow/tools/pip_package
https://blog.csdn.net/hedongya/article/details/79671469

TensorFlow学习一:源码安装 (参考)  结合tensorflow实战书籍(tensorflow也安装了好久,之前安装版本一直就是cpu版本,虽然下载的GPU版本,但是一跑实验用的就是CPU,因为用的是conda或者pip安装,而且还有很多潜在版本问题。而用源码安装就没有这么多问题,但是要主要使用的python和pip安装位置是否一致)
https://blog.csdn.net/u013832707/article/details/73161071

如何在Anaconda的python和系统自带的python之间切换(关于这个问题在源码安装TensorFlow过程中困扰了我许久,使用tensorflow-master在cuda9.1cudnn7.0.5上安装成功,但是却总是导入tensorflow失败,显示没有该模块,关键原因在经理无数次安装成功和导入失败之后至于发现,是由于最后一步使用pip安装是安装在系统自带python目录下,而默认Python使用的是anaconda2下面的Python,所以导致出错) /usr/bin/python
https://blog.csdn.net/teeyohuang/article/details/79076821
https://www.zhihu.com/question/48330791


facebookresearch/Detectron      https://github.com/facebookresearch/Detectron

install Caffe2   https://caffe2.ai/docs/getting-started.html?platform=ubuntu&configuration=compile

ubuntu下无root权限下用anaconda2安装caffe2 采坑日记!

https://blog.csdn.net/xuluohongshang/article/details/79280100

ubuntu16.04 grub rescue 模式下修复    http://www.cnblogs.com/sddai/p/7214330.html

ubuntu16.04引导错误修复    https://blog.csdn.net/abcsunl/article/details/72875983

(ubuntu16.04中磁盘空间被错误日志占满)我之前修改了usr的权限,导致开机进不去,猜测了很多原因,试了很多方法,之前遇到开机卡住是显卡驱动冲突,这次差点又要重新卸载,重装caffe。。。原来是usr权限被我设置成777用来拷文件进去,之后开机修改了引导项却因为空间被错误日志占满而开不了机。。。期间还出现了修复grub之后开机无线网搜索不到,然后重启几次就有进不去系统,现在看来就是usr权限被修改之后日志文件指数增长导致系统盘爆炸。之前搜的那个解决sudo命令是用不了的方法导致入坑。。。https://blog.csdn.net/yiscola/article/details/61638012

sudo:must be setuid root问题   https://www.linuxidc.com/Linux/2013-06/86245.htm

 Caffe2 - Detectron 初步使用  https://blog.csdn.net/zziahgf/article/details/79142978

使用Mask RCNN前的自己数据集的准备

https://baijiahao.baidu.com/s?id=1593798547829047940&wfr=spider&for=pc

labelme  https://github.com/wkentaro/labelme

【目标检测】Windows下安装图片标注工具labelme(安装labelme使用 )(重点

https://blog.csdn.net/disiwei1012/article/details/79508954






                                                                     

猜你喜欢

转载自blog.csdn.net/CPFelix/article/details/79869957
今日推荐