FCHD-Fully-Convolutional-Head-Detector

FCHD-Fully-Convolutional-Head-Detector copied to clipboard

为什么做了pytorch的数据增强后效果反而变差了

4

为了提高模型的精度，我想到了如下三个办法1：做增量训练，2：改用Adam优化器，暂时还没有成功，具体报错是数据格式的问题，我稍后再尝试一下,3:做数据增强，可是模型评估的系数一直很低，所以想请教一下有什么办法提议提高模型的精确度，还有就是判断标准就就仅仅看每一个epochs后打印的那个准确值吗??在一定的epoch后选择一个最好的模型再继续往下训练会有效果吗？？个人感觉会过拟合，而且评估系数只会越来越低，这又该如何解释呢。

KelvinHuang666

Fixes all the issues currently affecting the head detection demo

1

Specifically. - Fixed #22 , also added instructions in the README. - Fixed #15 , Applied the necessary changes directly in the code. - Added instructions in the README to...

IAmSuyogJadhav

damon2hang

Which dataset we can use without Brainwash?

2

There is unavailable Brainwash dataset. Which dataset we can use?

Fazyl03

build error

2

when I try python build.py build_ext --inplace I met error as follows:  could anybody give me some advice??thank you very much and thank for author`s great job

leijuzi

hi, python head_detection_demo.py have error

1

python head_detection_demo.py --img_path /home/fwq/pic/1.png --model_path /home/fwq/zhanghongruils/head/fchd/model/head_detector_final info: the python code for non_maximum_suppression is about 2x slow It is strongly recommended to build cython code: `cd model/utils/nms/; python3 build.py build_ext --inplace...

zhanghongruiupup

**Fixes provide by pull request #38** of @IAmSuyogJadhav : - Fixes #22, also added instructions in the README. - Fixed #15, Applied the necessary changes directly in the code. Added...

romamartyanov

I would like to know whether this paper is a journal paper or a conference paper, and I can't find the journal or conference to which this paper belongs, how...

circlety

Not performing well for dense crowd

3

Got very unsatisfactory on these kind of images. Am I doing something wrong? 

ghost

problem about single person

4

Dear author Thanks for supplying such wonderful work. Recently, I tried your work and found that when I use my own picture which contain one person. It seemd not work...

Angel113110