Faces dataset extension scripts for py-faster-rcnn

[Asiapenolove]

Hi, I think there are some requirement for face detections using py-faster-rcnn
so, I upload my implement script for fetching/handling data, and training prototxt

as build up py-faster-run (i.e. ./tools/demo.py runs properly) .

1. get a fine-tuned VGG16 model using py-faster-rcnn original script

./data/scripts/fetch_imagenet_models.sh

2. geting FDDB data set and training:

./data/scripts/get_FaceData.sh FDDB
./experiments/scripts/faster_rcnn_end2end.sh 0 VGG16 FDDB

3. geting WIDER data set and training :
   WIDER data needed to be downloaded here(http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/)

./data/scripts/get_FaceData.sh WIDER
./experiments/scripts/faster_rcnn_end2end.sh 0 VGG16 WIDER

[Asiapenolove]

I'm sorry that I'm new to git, not familiar with project handling, so there are many naive commits and messy scripts. Maybe someone can tell me how to improve scripts qualities.

[karaspd]

@Asiapenolove I am trying to use your script for WIDER dataset but I am getting some error, it might be because train.mat is corrupted, I tried to download it again but still get the same problem.
mat_f=hdf5storage.loadmat(mat_file)
File "/usr/local/lib/python2.7/dist-packages/hdf5storage/init.py", line 1768, in loadmat
with h5py.File(filename, mode='r') as f:
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open

It would be great either you could share wider_face_train.mat or your created xywhfile.txt file then maybe I can be able to reproduce your results. Thank you