登录
首页 » Python » py-faster-rcnn-master

py-faster-rcnn-master

于 2020-12-11 发布 文件大小:654KB
0 278
下载积分: 1 下载次数: 14

代码说明:

  图像检测的算法,Faster R-CNN算法,先对整张图像进行卷积计算,然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合,得到候选区域对应的特征矢量,这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一,方便后续的分类工作。通过感兴趣区域池化层处理卷积特征,并将得到的特征送往两个并行计算任务进行训练,分类和定位回归。通过这些方法和改进的框架,Fast R-CNN 用更短的训练和测试时长,取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)

文件列表:

py-faster-rcnn-master\.gitignore, 84 , 2018-12-17
py-faster-rcnn-master\.gitmodules, 131 , 2018-12-17
py-faster-rcnn-master\data\.gitignore, 70 , 2018-12-17
py-faster-rcnn-master\data\demo\000456.jpg, 105302 , 2018-12-17
py-faster-rcnn-master\data\demo\000542.jpg, 115536 , 2018-12-17
py-faster-rcnn-master\data\demo\001150.jpg, 88635 , 2018-12-17
py-faster-rcnn-master\data\demo\001763.jpg, 73424 , 2018-12-17
py-faster-rcnn-master\data\demo\004545.jpg, 123072 , 2018-12-17
py-faster-rcnn-master\data\pylintrc, 56 , 2018-12-17
py-faster-rcnn-master\data\README.md, 2516 , 2018-12-17
py-faster-rcnn-master\data\scripts\fetch_faster_rcnn_models.sh, 842 , 2018-12-17
py-faster-rcnn-master\data\scripts\fetch_imagenet_models.sh, 825 , 2018-12-17
py-faster-rcnn-master\data\scripts\fetch_selective_search_data.sh, 858 , 2018-12-17
py-faster-rcnn-master\experiments\cfgs\faster_rcnn_alt_opt.yml, 78 , 2018-12-17
py-faster-rcnn-master\experiments\cfgs\faster_rcnn_end2end.yml, 227 , 2018-12-17
py-faster-rcnn-master\experiments\logs\.gitignore, 7 , 2018-12-17
py-faster-rcnn-master\experiments\README.md, 185 , 2018-12-17
py-faster-rcnn-master\experiments\scripts\faster_rcnn_alt_opt.sh, 1509 , 2018-12-17
py-faster-rcnn-master\experiments\scripts\faster_rcnn_end2end.sh, 1781 , 2018-12-17
py-faster-rcnn-master\experiments\scripts\fast_rcnn.sh, 1448 , 2018-12-17
py-faster-rcnn-master\lib\datasets\coco.py, 16560 , 2018-12-17
py-faster-rcnn-master\lib\datasets\ds_utils.py, 1336 , 2018-12-17
py-faster-rcnn-master\lib\datasets\factory.py, 1403 , 2018-12-17
py-faster-rcnn-master\lib\datasets\imdb.py, 9811 , 2018-12-17
py-faster-rcnn-master\lib\datasets\pascal_voc.py, 14217 , 2018-12-17
py-faster-rcnn-master\lib\datasets\tools\mcg_munge.py, 1451 , 2018-12-17
py-faster-rcnn-master\lib\datasets\VOCdevkit-matlab-wrapper\get_voc_opts.m, 231 , 2018-12-17
py-faster-rcnn-master\lib\datasets\VOCdevkit-matlab-wrapper\voc_eval.m, 1332 , 2018-12-17
py-faster-rcnn-master\lib\datasets\VOCdevkit-matlab-wrapper\xVOCap.m, 258 , 2018-12-17
py-faster-rcnn-master\lib\datasets\voc_eval.py, 6938 , 2018-12-17
py-faster-rcnn-master\lib\datasets\__init__.py, 248 , 2018-12-17
py-faster-rcnn-master\lib\fast_rcnn\bbox_transform.py, 2540 , 2018-12-17
py-faster-rcnn-master\lib\fast_rcnn\config.py, 9213 , 2018-12-17
py-faster-rcnn-master\lib\fast_rcnn\nms_wrapper.py, 642 , 2018-12-17
py-faster-rcnn-master\lib\fast_rcnn\test.py, 11120 , 2018-12-17
py-faster-rcnn-master\lib\fast_rcnn\train.py, 6076 , 2018-12-17
py-faster-rcnn-master\lib\fast_rcnn\__init__.py, 248 , 2018-12-17
py-faster-rcnn-master\lib\Makefile, 56 , 2018-12-17
py-faster-rcnn-master\lib\nms\.gitignore, 15 , 2018-12-17
py-faster-rcnn-master\lib\nms\cpu_nms.pyx, 2241 , 2018-12-17
py-faster-rcnn-master\lib\nms\gpu_nms.hpp, 146 , 2018-12-17
py-faster-rcnn-master\lib\nms\gpu_nms.pyx, 1110 , 2018-12-17
py-faster-rcnn-master\lib\nms\nms_kernel.cu, 5064 , 2018-12-17
py-faster-rcnn-master\lib\nms\py_cpu_nms.py, 1051 , 2018-12-17
py-faster-rcnn-master\lib\nms\__init__.py, 0 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\coco.py, 14881 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\cocoeval.py, 19735 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\license.txt, 1533 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\mask.py, 4058 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\maskApi.c, 7704 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\maskApi.h, 1928 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\UPSTREAM_REV, 80 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\_mask.pyx, 10709 , 2018-12-17
py-faster-rcnn-master\lib\pycocotools\__init__.py, 21 , 2018-12-17
py-faster-rcnn-master\lib\roi_data_layer\layer.py, 7450 , 2018-12-17
py-faster-rcnn-master\lib\roi_data_layer\minibatch.py, 8169 , 2018-12-17
py-faster-rcnn-master\lib\roi_data_layer\roidb.py, 5611 , 2018-12-17
py-faster-rcnn-master\lib\roi_data_layer\__init__.py, 248 , 2018-12-17
py-faster-rcnn-master\lib\rpn\anchor_target_layer.py, 11344 , 2018-12-17
py-faster-rcnn-master\lib\rpn\generate.py, 3894 , 2018-12-17
py-faster-rcnn-master\lib\rpn\generate_anchors.py, 3110 , 2018-12-17
py-faster-rcnn-master\lib\rpn\proposal_layer.py, 6803 , 2018-12-17
py-faster-rcnn-master\lib\rpn\proposal_target_layer.py, 7495 , 2018-12-17
py-faster-rcnn-master\lib\rpn\README.md, 780 , 2018-12-17
py-faster-rcnn-master\lib\rpn\__init__.py, 262 , 2018-12-17
py-faster-rcnn-master\lib\setup.py, 5665 , 2018-12-17
py-faster-rcnn-master\lib\transform\torch_image_transform_layer.py, 2000 , 2018-12-17
py-faster-rcnn-master\lib\transform\__init__.py, 0 , 2018-12-17
py-faster-rcnn-master\lib\utils\.gitignore, 9 , 2018-12-17
py-faster-rcnn-master\lib\utils\bbox.pyx, 1756 , 2018-12-17
py-faster-rcnn-master\lib\utils\blob.py, 1625 , 2018-12-17
py-faster-rcnn-master\lib\utils\timer.py, 948 , 2018-12-17
py-faster-rcnn-master\lib\utils\__init__.py, 248 , 2018-12-17
py-faster-rcnn-master\LICENSE, 3745 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG16\faster_rcnn_end2end\solver.prototxt, 387 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG16\faster_rcnn_end2end\test.prototxt, 8754 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG16\faster_rcnn_end2end\train.prototxt, 9840 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG16\fast_rcnn\solver.prototxt, 395 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG16\fast_rcnn\test.prototxt, 6774 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG16\fast_rcnn\train.prototxt, 6625 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG_CNN_M_1024\faster_rcnn_end2end\solver.prototxt, 392 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG_CNN_M_1024\faster_rcnn_end2end\test.prototxt, 6973 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG_CNN_M_1024\faster_rcnn_end2end\train(1).prototxt, 7282 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG_CNN_M_1024\fast_rcnn\solver.prototxt, 398 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG_CNN_M_1024\fast_rcnn\test.prototxt, 4037 , 2018-12-17
py-faster-rcnn-master\models\coco\VGG_CNN_M_1024\fast_rcnn\train.prototxt, 4051 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\faster_rcnn_test.pt, 6263 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\rpn_test.pt, 5305 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage1_fast_rcnn_solver30k40k.pt, 390 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage1_fast_rcnn_train.pt, 8241 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage1_rpn_solver60k80k.pt, 378 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage1_rpn_train.pt, 8062 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage2_fast_rcnn_solver30k40k.pt, 390 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage2_fast_rcnn_train.pt, 8337 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage2_rpn_solver60k80k.pt, 378 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_alt_opt\stage2_rpn_train.pt, 8126 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_end2end\solver.prototxt, 407 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_end2end\test.prototxt, 8945 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_end2end\train.prototxt, 10209 , 2018-12-17
py-faster-rcnn-master\models\pascal_voc\VGG16\fast_rcnn\solver.prototxt, 400 , 2018-12-17

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论

0 个回复

  • project2_students
    基于互信息的刚性配准,利用了Powell算法和黄金分割算法,效果还不错(Based on Mutual Information rigid registration, Powell algorithm and the use of the golden section algorithm, the results were good)
    2015-12-18 14:36:54下载
    积分:1
  • dwt
    使用matlab实现的小波变换彩色图像水印嵌入和提取程序(Realize the use of matlab wavelet transform color image watermark embedding and extraction procedures)
    2008-03-03 23:23:54下载
    积分:1
  • main
    matlab实现的小波降噪声图像处理算法,效果十分好,自己做了调试。(The wavelet reduced noise image processing algorithm realized by Matlab is very effective and has been debugged.)
    2018-01-07 20:50:27下载
    积分:1
  • estimate
    对清晰图像加模糊并用时域和频域的方法分别实现对模糊参数的估计并将图像复原(其中用频域的方法实现对模糊角度的估计)(Clear picture of the additive fuzzy and time-domain and frequency domain methods, respectively, to achieve the estimated fuzzy parameters and image restoration (including the method used to achieve frequency domain point of view of fuzzy estimates))
    2009-05-23 21:51:47下载
    积分:1
  • qushuiyin
    一个去水印的程序,已调好。里边包含实例图片,可以帮助大家理解这个代码。(A program to watermark has a good tune. Inside contains examples of pictures that can help us to understand the code.)
    2013-10-13 23:27:47下载
    积分:1
  • shuzi
    数字识别PCA方法,对其它图像同样适用,程序简便。(Digital identification PCA method, on the other images of the same application, the program is simple.)
    2012-03-10 18:43:48下载
    积分:1
  • sift
    SIFT,即尺度不变特征变换(Scale-invariant feature transform,SIFT),是用于图像处理领域的一种描述。这种描述具有尺度不变性,可在图像中检测出关键点,是一种局部特征描述子。 该方法于 1999 年由 David Lowe 首先发表于计算机视觉国际会议(International Conference on Computer Vision,ICCV),2004 年再次经 David Lowe 整理完善后发表于 International journal of computer vision(IJCV) 。截止 2014 年 8 月,该论文单篇被引次数达 25000 余次。(来自百度)(SIFT, namely Scale-invariant feature transform (SIFT), is a description used in the field of image processing. This description has scale invariance and can detect key points in images. It is a local feature descriptor. This method was first published by David Lowe at the International Conference on Computer Vision (ICCV) in 1999 and published in the International Journal of Computer Vision (IJCV) in 2004 after it was sorted out and perfected by David Lowe again. As of August 2014, more than 25,000 citations have been cited. (From Baidu))
    2019-07-08 09:34:31下载
    积分:1
  • Fakecolor
    System Generator中伪彩色增强建模(Pseudocolor enhancement model in the System Generator)
    2021-03-30 16:19:09下载
    积分:1
  • MeanShift +Kalman(上传至Pudn)
    基于Kalman滤波和Meanshift算法的目标跟踪算法的C++程序,运行可用,具有参考价值。(The C++ program of target tracking algorithm based on Kalman filter and Mianshift algorithm is available and has reference value.)
    2018-09-17 15:33:14下载
    积分:1
  • OMP
    小波域稀疏表示,正交匹配追踪算法压缩感知重建(wavelet transform Compressive sensing)
    2019-03-11 16:13:23下载
    积分:1
  • 696516资源总数
  • 106914会员总数
  • 0今日下载