faster-rcnn训练自己的数据集——备忘

class xingren(imdb):　　　　　　　　#以下全是在构建这个 xingren 类
    def __init__(self, image_set, devkit_path=None):  # modified
        imdb.__init__(self, image_set)
        self._image_set = image_set　　　　#图片总文件夹存储在datasets目录下的位置　eg. xingren 
        self._devkit_path =  devkit_path   #根路径  /home/cc/py-faster-rcnn/lib/datasets
        self._data_path = os.path.join(self._devkit_path,image_set)   
　　　　　　　　　　#上句操作等同==>self._data_path='/home/cc/py-faster-rcnn/lib/datasets/xingren' 
        self._classes = ('__background__', # always index 0
                         'person')   #two classes
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes))) # form the dict{'__background__':'0','person':'1'}
        self._image_ext = '.jpg'  #根据自己图片的格式，我用的.png也没问题
        self._image_index = self._load_image_set_index('ImageList.txt') #加载样本的list.txt文件,需要注意路径是从 'lib/datasets/'下开始的。
    
        #******(该函数其余部分不做修改）

def image_path_from_index(self, index): #modified
    """
    Construct an image path from the image's "index" identifier.
    """
    image_path = os.path.join(self._data_path,'Images',index +'.jpg') #index就是从list.txt中读取的图片名
    assert os.path.exists(image_path), \
            'Path does not exist: {}'.format(image_path)
    return image_path

def _load_image_set_index(self,imagelist): # modified
    """
    Load the indexes listed in this dataset's image set file.
    """
    # Example path to image set file:
    # self._devkit_path + /VOCdevkit2007/VOC2007/ImageSets/Main/val.txt
    image_set_file = os.path.join(self._data_path, 'Imagelist',imagelist)
    assert os.path.exists(image_set_file), \
            'Path does not exist: {}'.format(image_set_file)
    with open(image_set_file) as f:
        image_index = [x.strip() for x in f.readlines()]
    return image_index

def _load_pascal_annotation(self, index):    #modified
    """
    Load image and bounding boxes info from XML file in the PASCAL VOC
    format.
    """
    filename = os.path.join(self._data_path, 'Annotations', index + '.xml')
    tree = ET.parse(filename)
    objs = tree.findall('object')

from datasets.xingren import xingren
d = xingren('xingren', '/home/cc/py-faster-rcnn/lib/datasets/')
res = d.roidb
from IPython import embed; embed()

# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------

"""Factory method for easily getting imdbs by name."""

__sets = {}

from datasets.xingren import xingren
import numpy as np

# # Set up voc_<year>_<split> using selective search "fast" mode
# for year in ['2007', '2012']:
#     for split in ['train', 'val', 'trainval', 'test']:
#         name = 'voc_{}_{}'.format(year, split)
#         __sets[name] = (lambda split=split, year=year: pascal_voc(split, year))
#
# # Set up coco_2014_<split>
# for year in ['2014']:
#     for split in ['train', 'val', 'minival', 'valminusminival']:
#         name = 'coco_{}_{}'.format(year, split)
#         __sets[name] = (lambda split=split, year=year: coco(split, year))
#
# # Set up coco_2015_<split>
# for year in ['2015']:
#     for split in ['test', 'test-dev']:
#         name = 'coco_{}_{}'.format(year, split)
#         __sets[name] = (lambda split=split, year=year: coco(split, year))

name = 'xingren'
devkit = '/home/cc/py-faster-rcnn/lib/datasets/'
__sets['xingren'] = (lambda name = name,devkit = devkit: xingren(name,devkit))

def get_imdb(name):
    """Get an imdb (image database) by name."""
    if not __sets.has_key(name):
        raise KeyError('Unknown dataset: {}'.format(name))
    return __sets[name]()

def list_imdbs():
    """List all registered imdbs."""
    return __sets.keys()