Faster R-CNN源代码(TF)--datasets/pascal_voc.py

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

import os
from datasets.imdb import imdb
import datasets.ds_utils as ds_utils
import xml.etree.ElementTree as ET
import numpy as np
import scipy.sparse
import scipy.io as sio
import utils.cython_bbox
import cPickle
import subprocess
import uuid
from voc_eval import voc_eval
from fast_rcnn.config import cfg
import pdb


class pascal_voc(imdb):
    def __init__(self, image_set, year, devkit_path=None):
        #构造函数参数分别是数据集类型，版本以及一个path
        #例如train，2007这样子，然后调用父类imdb的构造函数，参数例如voc_2007_train
        imdb.__init__(self, 'voc_' + year + '_' + image_set)
        self._year = year
        self._image_set = image_set
        #如果参数devkit_path是空的情况，那么_devkit_path设置成_get_default_path()
        #即“Fsater-RCNN_TF/data/VOCdevkit2007”
        self._devkit_path = self._get_default_path() if devkit_path is None \
                            else devkit_path
        self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
        #父类的_classes
        self._classes = ('__background__', # always index 0
                         'aeroplane', 'bicycle', 'bird', 'boat',
                         'bottle', 'bus', 'car', 'cat', 'chair',
                         'cow', 'diningtable', 'dog', 'horse',
                         'motorbike', 'person', 'pottedplant',
                         'sheep', 'sofa', 'train', 'tvmonitor')
        #class对应索引，例如{'__background__':0,'aeroplane':1,...}
        self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
        self._image_ext = '.jpg'
        #加载图片的索引[00000,00001,00002,...]
        self._image_index = self._load_image_set_index()
        # Default to roidb handler
        #self._roidb_handler = self.selective_search_roidb
        self._roidb_handler = self.gt_roidb
        self._salt = str(uuid.uuid4())
        self._comp_id = 'comp4'

        # PASCAL specific config options
        self.config = {'cleanup'     : True,
                       'use_salt'    : True,
                       'use_diff'    : False,
                       'matlab_eval' : False,
                       'rpn_file'    : None,
                       'min_size'    : 2}

        assert os.path.exists(self._devkit_path), \
                'VOCdevkit path does not exist: {}'.format(self._devkit_path)
        assert os.path.exists(self._data_path), \
                'Path does not exist: {}'.format(self._data_path)

    def image_path_at(self, i):
        #重载了父类的方法，返回某一个index的图片路径
        """
        Return the absolute path to image i in the image sequence.
        """
        return self.image_path_from_index(self._image_index[i])

    def image_path_from_index(self, index):
        #被上面的函数调用
        #返回“....../JPEGIMages/00000.jpg”
        """
        Construct an image path from the image's "index" identifier.
        """
        image_path = os.path.join(self._data_path, 'JPEGImages',
                                  index + self._image_ext)
        assert os.path.exists(image_path), \
                'Path does not exist: {}'.format(image_path)
        return image_path

    def _load_image_set_index(self):
        #从txt文件加载数据集的index
        #例如从train.txt加载index
        """
        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, 'ImageSets', 'Main',
                                      self._image_set + '.txt')
        assert os.path.exists(image_set_file), \
                'Path does not exist: {}'.format(image_set_file)
        #strip()去掉前后的空格
        with open(image_set_file) as f:
            image_index = [x.strip() for x in f.readlines()]
        return image_index

    def _get_default_path(self):
        #返回数据集的根目录
        """
        Return the default path where PASCAL VOC is expected to be installed.
        """
        return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)

    def gt_roidb(self):
        """
        Return the database of ground-truth regions of interest.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        #函数得到roi的数据
        #组合cache_file的路径
        #例如Fsater-RCNN_TF/data/cache/voc_2007_train__gt_roidb.pkl
        cache_file = os.path.join(self.cache_path, self.name + '_gt_roidb.pkl')

        #如果已经存在cache文件，那么就加载到roidb里，然后返回

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} gt roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        #不存在的话，就去标注文件里加载，返回一个list，每一个元素是一张图片对应的字典
        gt_roidb = [self._load_pascal_annotation(index)
                    for index in self.image_index]

        #写入cache文件
        with open(cache_file, 'wb') as fid:
            cPickle.dump(gt_roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote gt roidb to {}'.format(cache_file)

        #返回roidb
        return gt_roidb

    def selective_search_roidb(self):
        """
        Return the database of selective search regions of interest.
        Ground-truth ROIs are also included.

        This function loads/saves from/to a cache file to speed up future calls.
        """
        cache_file = os.path.join(self.cache_path,
                                  self.name + '_selective_search_roidb.pkl')

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as fid:
                roidb = cPickle.load(fid)
            print '{} ss roidb loaded from {}'.format(self.name, cache_file)
            return roidb

        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            ss_roidb = self._load_selective_search_roidb(gt_roidb)
            roidb = imdb.merge_roidbs(gt_roidb, ss_roidb)
        else:
            roidb = self._load_selective_search_roidb(None)
        with open(cache_file, 'wb') as fid:
            cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)
        print 'wrote ss roidb to {}'.format(cache_file)

        return roidb

    def rpn_roidb(self):
        if int(self._year) == 2007 or self._image_set != 'test':
            gt_roidb = self.gt_roidb()
            rpn_roidb = self._load_rpn_roidb(gt_roidb)
            roidb = imdb.merge_roidbs(gt_roidb, rpn_roidb)
        else:
            roidb = self._load_rpn_roidb(None)

        return roidb

    def _load_rpn_roidb(self, gt_roidb):
        filename = self.config['rpn_file']
        print 'loading {}'.format(filename)
        assert os.path.exists(filename), \
               'rpn data not found at: {}'.format(filename)
        with open(filename, 'rb') as f:
            box_list = cPickle.load(f)
        return self.create_roidb_from_box_list(box_list, gt_roidb)

    def _load_selective_search_roidb(self, gt_roidb):
        filename = os.path.abspath(os.path.join(cfg.DATA_DIR,
                                                'selective_search_data',
                                                self.name + '.mat'))
        assert os.path.exists(filename), \
               'Selective search data not found at: {}'.format(filename)
        raw_data = sio.loadmat(filename)['boxes'].ravel()

        box_list = []
        for i in xrange(raw_data.shape[0]):
            boxes = raw_data[i][:, (1, 0, 3, 2)] - 1
            keep = ds_utils.unique_boxes(boxes)
            boxes = boxes[keep, :]
            keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])
            boxes = boxes[keep, :]
            box_list.append(boxes)

        return self.create_roidb_from_box_list(box_list, gt_roidb)

    def _load_pascal_annotation(self, index):
        """
        Load image and bounding boxes info from XML file in the PASCAL VOC
        format.
        """
        #加载PASCAL数据集中某一个图片的标注，返回一个字典
        #例如{'boxes' : [[x1,y1,x2,y2],[x1,y1,x2,y2],...],
        #    'gt_classes': 0表示background，1表示飞机...
        #    'gt_overlaps' : overlaps, onehot编码的类别
        #    'flipped' : False,
        #    'seg_areas' : seg_areas}  #obj的面积
        filename = os.path.join(self._data_path, 'Annotations', index + '.xml')
        tree = ET.parse(filename)
        objs = tree.findall('object')
        if not self.config['use_diff']:
            # Exclude the samples labeled as difficult
            non_diff_objs = [
                obj for obj in objs if int(obj.find('difficult').text) == 0]
            # if len(non_diff_objs) != len(objs):
            #     print 'Removed {} difficult objects'.format(
            #         len(objs) - len(non_diff_objs))
            objs = non_diff_objs
        num_objs = len(objs)
        #boxes的shape是bbox个数*4
        boxes = np.zeros((num_objs, 4), dtype=np.uint16)

        #gt_classes的shape是bbox个数
        gt_classes = np.zeros((num_objs), dtype=np.int32)

        #overlaps的shape是bbox个数*class个数
        overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)

        # bbox的面积
        seg_areas = np.zeros((num_objs), dtype=np.float32)

        # Load object bounding boxes into a data frame.
        for ix, obj in enumerate(objs):
            bbox = obj.find('bndbox')
            # Make pixel indexes 0-based
            x1 = float(bbox.find('xmin').text) - 1
            y1 = float(bbox.find('ymin').text) - 1
            x2 = float(bbox.find('xmax').text) - 1
            y2 = float(bbox.find('ymax').text) - 1
            cls = self._class_to_ind[obj.find('name').text.lower().strip()]
            boxes[ix, :] = [x1, y1, x2, y2]
            gt_classes[ix] = cls
            overlaps[ix, cls] = 1.0
            seg_areas[ix] = (x2 - x1 + 1) * (y2 - y1 + 1)

        #对onehot进行稀疏矩阵压缩，节省内存
        overlaps = scipy.sparse.csr_matrix(overlaps)

        #总结类型：以下key的类型依次为array、array、scipy.sparse.csr.csr_matrix、bool、array
        return {'boxes' : boxes,
                'gt_classes': gt_classes,
                'gt_overlaps' : overlaps,
                'flipped' : False,
                'seg_areas' : seg_areas}

    def _get_comp_id(self):
        comp_id = (self._comp_id + '_' + self._salt if self.config['use_salt']
            else self._comp_id)
        return comp_id

    def _get_voc_results_file_template(self):
        #函数是返回一个
        #
        # VOCdevkit/results/VOC2007/Main/<comp_id>_det_test_aeroplane.txt
        filename = self._get_comp_id() + '_det_' + self._image_set + '_{:s}.txt'
        path = os.path.join(
            self._devkit_path,
            'results',
            'VOC' + self._year,
            'Main',
            filename)
        return path

    def _write_voc_results_file(self, all_boxes):
        for cls_ind, cls in enumerate(self.classes):
            if cls == '__background__':
                continue
            print 'Writing {} VOC results file'.format(cls)
            filename = self._get_voc_results_file_template().format(cls)
            with open(filename, 'wt') as f:
                for im_ind, index in enumerate(self.image_index):
                    dets = all_boxes[cls_ind][im_ind]
                    if dets == []:
                        continue
                    # the VOCdevkit expects 1-based indices
                    for k in xrange(dets.shape[0]):
                        f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'.
                                format(index, dets[k, -1],
                                       dets[k, 0] + 1, dets[k, 1] + 1,
                                       dets[k, 2] + 1, dets[k, 3] + 1))

    def _do_python_eval(self, output_dir = 'output'):
        #这个方法是最终对模型评测的函数，最终将每个类的评测结果写入文件以及输出到控制台
        #annopath组合出标注文件的路径，例“Fsater-RCNN_TF/data/VOCdevkit2007/Annotations/{}.xml”
        #括号里的内容在调用的函数voc_eval里会给入
        annopath = os.path.join(
            self._devkit_path,
            'VOC' + self._year,
            'Annotations',
            '{:s}.xml')

        #imagesetfile组合出原始图片索引文件的路径。例如“Fsater-RCNN_TF/data/VOCdevkit2007/ImageSets/Main/train.txt”
        imagesetfile = os.path.join(
            self._devkit_path,
            'VOC' + self._year,
            'ImageSets',
            'Main',
            self._image_set + '.txt')

        #cachedir组合出cache文件的路径。例如“Fsater-RCNN_TF/data/VOCdevkit2007/annotations_cache”
        cachedir = os.path.join(self._devkit_path, 'annotations_cache')

        #aps是一组ap的列表，每一个元素存储一个类的ap
        aps = []

        #度量方法从pascal2010开始变化了，所以之前的数据集按照2007的标准
        # The PASCAL VOC metric changed in 2010
        use_07_metric = True if int(self._year) < 2010 else False
        print 'VOC07 metric? ' + ('Yes' if use_07_metric else 'No')

        #如果没有输出最终结果的文件夹，那么就创建
        if not os.path.isdir(output_dir):
            os.mkdir(output_dir)

        #枚举每一个类，enumerate返回值是两个，第一个是下标，第二个是类本身
        #比如(0,background),(1,aeroplane）...
        for i, cls in enumerate(self._classes):
            #背景这个类没必要评测，直接过
            if cls == '__background__':
                continue
            filename = self._get_voc_results_file_template().format(cls)

            #调用voc_eval.py中的voc_eval对每一个类进行评估，返回该类的召回率rec，查准率prec，以及ap
            rec, prec, ap = voc_eval(
                filename, annopath, imagesetfile, cls, cachedir, ovthresh=0.5,
                use_07_metric=use_07_metric)
            aps += [ap]
            print('AP for {} = {:.4f}'.format(cls, ap))
            with open(os.path.join(output_dir, cls + '_pr.pkl'), 'w') as f:
                cPickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)
        print('Mean AP = {:.4f}'.format(np.mean(aps)))
        print('~~~~~~~~')
        print('Results:')
        for ap in aps:
            print('{:.3f}'.format(ap))
        print('{:.3f}'.format(np.mean(aps)))
        print('~~~~~~~~')
        print('')
        print('--------------------------------------------------------------')
        print('Results computed with the **unofficial** Python eval code.')
        print('Results should be very close to the official MATLAB eval code.')
        print('Recompute with `./tools/reval.py --matlab ...` for your paper.')
        print('-- Thanks, The Management')
        print('--------------------------------------------------------------')

    def _do_matlab_eval(self, output_dir='output'):
        print '-----------------------------------------------------'
        print 'Computing results with the official MATLAB eval code.'
        print '-----------------------------------------------------'
        path = os.path.join(cfg.ROOT_DIR, 'lib', 'datasets',
                            'VOCdevkit-matlab-wrapper')
        cmd = 'cd {} && '.format(path)
        cmd += '{:s} -nodisplay -nodesktop '.format(cfg.MATLAB)
        cmd += '-r "dbstop if error; '
        cmd += 'voc_eval(\'{:s}\',\'{:s}\',\'{:s}\',\'{:s}\'); quit;"' \
               .format(self._devkit_path, self._get_comp_id(),
                       self._image_set, output_dir)
        print('Running:\n{}'.format(cmd))
        status = subprocess.call(cmd, shell=True)

    def evaluate_detections(self, all_boxes, output_dir):
        self._write_voc_results_file(all_boxes)
        self._do_python_eval(output_dir)
        if self.config['matlab_eval']:
            self._do_matlab_eval(output_dir)
        if self.config['cleanup']:
            for cls in self._classes:
                if cls == '__background__':
                    continue
                filename = self._get_voc_results_file_template().format(cls)
                os.remove(filename)

    def competition_mode(self, on):
        if on:
            self.config['use_salt'] = False
            self.config['cleanup'] = False
        else:
            self.config['use_salt'] = True
            self.config['cleanup'] = True

if __name__ == '__main__':
    from datasets.pascal_voc import pascal_voc
    d = pascal_voc('trainval', '2007')
    res = d.roidb
    from IPython import embed; embed()