kkkkkkkkq的博客

弄了好几天终于能在FDDB数据集上测试自己用wider face数据集训练的的faster rcnn的检测器的性能了。1、首先在官网http://vis-www.cs.umass.edu/fddb/index.html下载图片和标注文件，FDDB的标注文件，分为图片名称文件FDDB-fold-01.txt、对应的标注文件：FDDB-fold-01-ellispe.txt，各有10个，把

我是将数据转化为VOC格式，所以修改Deformable-ConvNets\lib\dataset\pascal_voc.py文件：注释掉load_pascal_annotation函数中filename = os.path.join(self.data_path, 'Annotations', index + '.xml') tree = ET.parse(filenam

UCCS数据集官网：http://vast.uccs.edu/Opensetface/head.xml widerface %06d.jpg My Database VOC2007 flickr NULL NULL facevise

1、首先训练时用wider face的训练集进行训练（不要用验证集）2、在http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/WiderFace_Results.html下载Evaluation code:Evaluation, Plotting scripts and the PR curves3、用wider face中的验证集val进行测试，得到检测...

Flowchart of the training procedureFirst of all, we train the CNN model of Faster RCNN using the WIDER FACE dataset [30]. Wefurther use the same dataset to test the pre-trained model so as t

网络结构：这篇文章在基于faster rcnn做了一些改进：First, based on a newly developed loss function called center loss [33], we design a new multi-taskloss function in the Fast R-CNN model to supervise the learning

head.xml widerface %06d.jpg My Database VOC2007 flickr NULL NULL facevise %d %d %d