- 博客(30)
- 资源 (4)
- 收藏
- 关注
原创 ubuntu 查找包含关键字的文件
如果想在当前文件夹查看后缀为.txt中含有“Base”关键字的文件,只需find ./ -name "*.txt" | xargs grep "Base"格式为:find 文件夹路径 -name "用通配符表示要搜索的文件" | xargs grep "要搜索的key值"对于通配符,根据自己需求进行修改,如 对.txt文件搜索为 “*.txt” 无要求(即所有文件全部搜...
2017-09-26 16:04:26 3973
原创 ubuntu修改图片格式(jpg、jpeg、pbm等)
方法一:imagemagick#安装sudo apt-get install imagemagick#转化convert 1.jpeg 1.jpg方法二:opencv#include <iostream>#include<opencv2/core/core.hpp> #include<opencv2/highgui/highgui....
2017-09-26 11:23:46 6512
原创 Faster-RCNN_TF代码解读20:blob.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-19 09:42:58 1322 1
原创 Faster-RCNN_TF代码解读19:bbox.pyx
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Sergey Karayev# ---------
2017-09-19 09:42:11 2499 1
原创 Faster-RCNN_TF代码解读18:generate_anchors.py
#-*- coding:utf-8 -*-# --------------------------------------------------------# Faster R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ro
2017-09-19 09:38:48 1017
原创 Faster-RCNN_TF代码解读17:anchor_target_layer_tf.py
# --------------------------------------------------------# Faster R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick and Sean B
2017-09-19 09:37:19 3315 2
原创 Faster-RCNN_TF代码解读16:roi_data_layer/roidb.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-19 09:35:07 2394
原创 Faster-RCNN_TF代码解读15:roi_data_layer/minibatch.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-19 09:32:24 1211
原创 Faster-RCNN_TF代码解读14:roi_data_layer/layer.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-19 09:30:04 1408
原创 Faster-RCNN_TF代码解读13:nms_wrapper.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-19 09:23:22 2351
原创 Faster-RCNN_TF代码解读12:bbox_transform.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-19 09:21:48 3728 3
原创 Faster-RCNN_TF代码解读11:imdb.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-19 09:20:12 2189
原创 Faster-RCNN_TF代码解读10:proposal_layer_tf.py
# --------------------------------------------------------# Faster R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick and Sean B
2017-09-18 16:31:10 2506 9
原创 Faster-RCNN_TF代码解读9:proposal_target_layer_tf.py
# --------------------------------------------------------# Faster R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick and Sean B
2017-09-18 16:26:37 4835 4
原创 Faster-RCNN_TF代码解读8:networks.py
import numpy as npimport tensorflow as tfimport roi_pooling_layer.roi_pooling_op as roi_pool_opimport roi_pooling_layer.roi_pooling_op_gradfrom rpn_msr.proposal_layer_tf import proposal_layer as pr
2017-09-18 16:21:49 3517
原创 Faster-RCNN_TF代码解读7:VGGnet_train.py
import tensorflow as tffrom networks.network import Network#definen_classes = 21_feat_stride = [16,]anchor_scales = [8, 16, 32]class VGGnet_train(Network): def __init__(self, trainable=True):
2017-09-18 16:17:55 1879 4
原创 Faster-RCNN_TF代码解读6:pascal_voc.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-18 16:12:55 3500 12
原创 Faster-RCNN_TF代码解读5:networks/factory.py
# --------------------------------------------------------# SubCNN_TF# Copyright (c) 2016 CVGL Stanford# Licensed under The MIT License [see LICENSE for details]# Written by Yu Xiang# ------------
2017-09-18 16:09:00 1183
原创 Faster-RCNN_TF代码解读4:config.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-18 16:06:31 3574
原创 Faster-RCNN_TF代码解读3:train.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-18 16:02:44 3171
原创 Faster-RCNN_TF代码解读2:datasets/factory.py
# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross Girshick# ----------
2017-09-18 15:59:51 1989
原创 Faster-RCNN_TF代码解读1:train-net.py
#!/usr/bin/env python# --------------------------------------------------------# Fast R-CNN# Copyright (c) 2015 Microsoft# Licensed under The MIT License [see LICENSE for details]# Written by Ross
2017-09-18 15:20:39 4872 2
原创 TypeError: slice indices must be integers or None or have an __index__ method
在训练faster-rcnn自己的网络结构和数据集时,出现了TypeError: slice indices must be integers or None or have an index method根据错误提示查看了当前出错的点的数据类型,一般为numpy.int32和numpy.float64。 但是这两种数据类型不能作为index(能作为index的只有int、None...
2017-09-17 18:47:20 1422 1
原创 python脚本制作dlib数据集
前提:你已经得到了预选框范围,来自动制作dlib数据集(xml),从而省去imglab花框过程 预选框文件内容格式(图片名,左上角x,左上角y,右下角x,右下角y),如:left_88.png 294 170 115 190 python脚本:root_path="'/home/ubuntu/sotfware/dlib-18.16-new/examples/tiaotong/"k=o...
2017-09-16 11:08:36 962
转载 python切片操作符 :与::
说明:切片操作符在python中的原型是[start:stop:step]即:[开始索引:结束索引:步长值]开始索引:同其它语言一样,从0开始。序列从左向右方向中,第一个值的索引为0,最后一个为-1结束索引:切片操作符将取到该索引为止,不包含该索引的值。步长值:默认是一个接着一个切取,如果为2,则表示进行隔一取一操作。步长值为正时表示从左向右取,如果为负,则表示从右向左取。步长值不能为0li = ...
2017-09-14 15:19:12 847
转载 train_val.prototxt和deploy.prototxt文件解读
转自:http://blog.csdn.net/fx409494616/article/details/53008971本文以CaffeNet为例:1. train_val.prototxt 首先,train_val.prototxt文件是网络配置文件。该文件是在训练的时候用的。2.deploy.prototxt该文件是在测试时使用的文件。区别:首先deploy.prototxt文件都是在trai...
2017-09-12 16:22:35 841
原创 ubuntu 14.04修改默认python版本
有时需要将ubuntu14.04默认的默认的python2.7版本修改为python3.4版本,只需1、删除旧的软链接sudo mv rm /usr/bin/python2、建立新的python3.4软链接sudo ln -s /usr/bin/ptyhon3.4 /usr/bin/python3、测试此时在终端输入:python或者...
2017-09-07 14:36:51 4012 3
转载 Python的星号(*、**)的作用
转载自:http://blog.csdn.net/liuxingen/article/details/501139231. 函数的可变参数当函数的参数前面有一个星号的时候表示这是一个可变的位置参数,两个星号*表示是可变的关键字参数。#!env python#coding=utf-8#def foo(*args, **kwarg): for item in args...
2017-09-07 11:21:57 715
原创 numpy数组遍历找到个数最多的元素
1、代码# -*- coding:utf-8 -*-import numpy as nparr=np.array([[7,7,2,1],[12,7,6,4],[6,6,7,9],[0,2,3,3]])tu=sorted([(np.sum(arr==i),i) for i in set(arr.flat)])print('个数最多元素为 {1} 有 {0} 个'.format(*t...
2017-09-07 11:15:00 6540
原创 ubuntu 安装 ipython notebook
此安装过程是在python2环境下,如果是python3只需将pip2改为pip31、安装pyzmqsudo pip2 install pyzmq2、安装tornadosudo pip2 install tornado3、安装jinja2sudo pip2 install jinja24、安装jsonschemasudo pip2 i...
2017-09-05 14:30:15 2656
用自己的数据制作python版本cifar10数据集
2017-05-03
NCVPixelOperations.hpp
2016-11-24
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人