04 2016 档案

Learn python the hard way. python test program 2016.04.27
摘要：class Song(object): def __init__(self, lyrics): self.lyrics = lyrics def sing_me_s_song(self): for line in self.lyrics: print line happy_bday = Song([ 阅读全文
posted @ 2016-04-27 20:26 AHU-WangXiao 阅读(250) 评论(0) 推荐(0)
caffe: train_loss_figure 2016.04.27
该文被密码保护。
posted @ 2016-04-27 16:04 AHU-WangXiao 阅读(3) 评论(0) 推荐(0)
论文笔记之：Active Object Localization with Deep Reinforcement Learning
摘要：Active Object Localization with Deep Reinforcement Learning ICCV 2015 最近Deep Reinforcement Learning算是火了一把，在Google Deep Mind的主页上，更是许多关于此的paper，基本都发在ICM 阅读全文
posted @ 2016-04-27 13:16 AHU-WangXiao 阅读(5466) 评论(10) 推荐(1)
如何用 matlab 在图片上绘制矩形框 和 添加文字 ？
摘要：如何给图像添加矩形框？以及添加想要输入的文字 ？ 案例程序，如下所示： clc; close all; clear all;image = imread('/home/wangxiao/Pictures/image/gamersky_022origin_043_20147261368D.jpg'); 阅读全文
posted @ 2016-04-26 20:35 AHU-WangXiao 阅读(10359) 评论(0) 推荐(0)
论文笔记之：Learning Deconvolution Network for Semantic Segmentation
该文被密码保护。
posted @ 2016-04-25 17:45 AHU-WangXiao 阅读(3) 评论(0) 推荐(0)
论文笔记之：Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
摘要：Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation xx 阅读全文
posted @ 2016-04-25 13:27 AHU-WangXiao 阅读(714) 评论(0) 推荐(0)
feature visualization from ipython notebook
摘要：Feature visualization from ipython notebook Wang Xiao 1. install anaconda2 from: https://www.continuum.io/downloads Note: download the version 2 not v 阅读全文
posted @ 2016-04-24 15:41 AHU-WangXiao 阅读(344) 评论(0) 推荐(0)
将caffe训练时loss的变化曲线用matlab绘制出来
摘要：1. 首先是提取 训练日志文件; 2. 然后是matlab代码： 3. 结果展示： 阅读全文
posted @ 2016-04-23 20:05 AHU-WangXiao 阅读(3520) 评论(0) 推荐(0)
how to change the AlexNet into FCNs ?
摘要：How to change the AlexNet into FCNs ? FCNs is a network that only contain convolution layers and no fc layer at all. It's structure can be shown as th 阅读全文
posted @ 2016-04-22 15:44 AHU-WangXiao 阅读(604) 评论(0) 推荐(0)
Experiments log ---- 2016.04.21
该文被密码保护。
posted @ 2016-04-21 21:20 AHU-WangXiao 阅读(4) 评论(0) 推荐(0)
论文笔记之：Towards Computational Baby Learning: A Weakly-supervised Approach for Object Detection
该文被密码保护。
posted @ 2016-04-21 16:17 AHU-WangXiao 阅读(3) 评论(0) 推荐(0)
论文笔记之：Instance-aware Semantic Segmentation via Multi-task Network Cascades
摘要：Instance-aware Semantic Segmentation via Multi-task Network Cascades Jifeng Dai Kaiming He Jian Sun 本文的出发点是做Instance-aware Semantic Segmentation，但是为了做 阅读全文
posted @ 2016-04-20 18:42 AHU-WangXiao 阅读(2895) 评论(0) 推荐(1)
论文笔记之：Pedestrian Detection aided by Deep Learning Semantic Tasks
摘要：Pedestrian Detection aided by Deep Learning Semantic Tasks CVPR 2015 本文考虑将语义任务（即：行人属性和场景属性）和行人检测相结合，以语义信息协助进行行人检测。先来看一下大致的检测结果（TA-CNN为本文检测结果）： 可以看出，由于 阅读全文
posted @ 2016-04-20 14:29 AHU-WangXiao 阅读(1161) 评论(0) 推荐(0)
feature的可视化
摘要：。。。 阅读全文
posted @ 2016-04-15 16:53 AHU-WangXiao 阅读(266) 评论(0) 推荐(0)
caffe 训练时，出现错误：Check failed: error == cudaSuccess (4 vs. 0) unspecified launch failure
摘要：I0415 15:03:37.603461 27311 solver.cpp:42] Solver scaffolding done.I0415 15:03:37.603549 27311 solver.cpp:247] Solving AlexNetI0415 15:03:37.603559 27 阅读全文
posted @ 2016-04-15 15:07 AHU-WangXiao 阅读(5894) 评论(2) 推荐(0)
peta results backUp : part train data baseline 6160 images and all train images used 9500 images
该文被密码保护。
posted @ 2016-04-15 14:51 AHU-WangXiao 阅读(4) 评论(0) 推荐(0)
论文笔记之：Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
该文被密码保护。
posted @ 2016-04-15 14:39 AHU-WangXiao 阅读(4) 评论(0) 推荐(0)
multi-softmax group-based attribute prototxt file backUp 2016.04.13
该文被密码保护。
posted @ 2016-04-13 21:08 AHU-WangXiao 阅读(2) 评论(0) 推荐(0)
Caffe+CUDA8.0+CuDNNv5.1+OpenCV3.1+Ubuntu14.04 配置参考文献 以及 常见编译问题总结
摘要：Ubuntu + Deep Learning (Caffe, PyTorch) 配置参考文献 sudo apt install nvidia-cuda-toolkit pip install gpustat watch --color -n1 gpustat -cpu [Note]: the RTX 阅读全文
posted @ 2016-04-13 10:11 AHU-WangXiao 阅读(28278) 评论(0) 推荐(0)
when compile /home/wangxiao/NVIDIA-CUDA-7.5 SAMPLES, it warning: gcc version larger than 4.9 not supported, so: old verson of gcc and g++ are needed
摘要：then, a link needed : 阅读全文
posted @ 2016-04-13 09:27 AHU-WangXiao 阅读(240) 评论(0) 推荐(0)
add new dataLayer to caffe, 　separateLabelLayer.cpp separateLabelLayer.hpp caffe.proto　　　(code backUp)
该文被密码保护。
posted @ 2016-04-08 16:47 AHU-WangXiao 阅读(3) 评论(0) 推荐(0)
image data layer back_up 2016.04.08
该文被密码保护。
posted @ 2016-04-08 13:45 AHU-WangXiao 阅读(1) 评论(0) 推荐(0)
caffe:编译时提示：unsupported GNU version! gcc versions later than 4.9 are not supported!
摘要：NVCC src/caffe/solvers/adam_solver.cuIn file included from /usr/local/cuda/include/cuda_runtime.h:76:0, from <command-line>:0:/usr/local/cuda/include/ 阅读全文
posted @ 2016-04-06 23:18 AHU-WangXiao 阅读(4348) 评论(0) 推荐(0)
如何给caffe添加新的layer ?
摘要：如何给caffe添加新的layer ? 初学caffe难免会遇到这个问题，网上搜来一段看似经典的话， 但是问题来了，貌似新版的caffe并没有上面提到的vision_layer： 阅读全文
posted @ 2016-04-06 21:20 AHU-WangXiao 阅读(280) 评论(0) 推荐(0)
PETA 成分分析之：无SPL,只用Group Priori （I）
该文被密码保护。
posted @ 2016-04-03 14:26 AHU-WangXiao 阅读(3) 评论(0) 推荐(0)