Faster Rcnn 代码解读之 factory.py

# --------------------------------------------------------
# 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."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

__sets = {}
from datasets.pascal_voc import pascal_voc
from datasets.coco import coco

import numpy as np

'''
本文件作用是把所有可能的dataset都列举一次
然后主函数调用时看看此时的dataset在不在之前列举都情况里
有就返回这个数据集类型的对象，没有就报错。
'''

# Set up voc_<year>_<split> 
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))

for year in ['2007', '2012']:
    for split in ['train', 'val', 'trainval', 'test']:
        name = 'voc_{}_{}_diff'.format(year, split)
        __sets[name] = (lambda split=split, year=year: pascal_voc(split, year, use_diff=True))

# Set up coco_2014_<split>
for year in ['2014']:
    for split in ['train', 'val', 'minival', 'valminusminival', 'trainval']:
        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))


def get_imdb(name):
    """Get an imdb (image database) by name."""
    # 判断有没有定义此数据集
    # _set为一个dict，存了几个数据集的名称
    if name not in __sets:
        raise KeyError('Unknown dataset: {}'.format(name))
    return __sets[name]()


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