# --------------------------------------------------------
# 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
#pascal_voc繼承imdb
class pascal_voc(imdb):
#傳進來的第一個參數為資料集名稱(train,val,test...),第二個參數為版本,如2007,devkit_path暫時為空
def __init__(self, image_set, year, devkit_path=None):
#調用imdb的構造函數,傳進去參數格式為“voc_year_imageset”--例如voc_2007_train,其實就是記錄了一下self._name,其餘的為預設,
#其餘預設參數有(self._num_classes,self._classes,self._image_index,self._obj_proposer,self._roidb,self._roidb_handler,self.config)
imdb.__init__(self, 'voc_' + year + '_' + image_set)
self._year = year
self._image_set = image_set
#devikit_path在不給定下為None,此時self._devkit_path為Fsater - RCNN_TF / data / VOCdevkit+self._year
self._devkit_path = self._get_default_path() if devkit_path is None \
else devkit_path
#為Fsater - RCNN_TF / data / VOCdevkit +'year'/'VOC' + self._year
self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
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')
#在imdb中定義self.classes即為self._classes,self.num_classes為len(self._classes)
#self._class_to_ind裡存的是{'__background__':0,'aeroplane':1.....}
self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
#圖檔格式
self._image_ext = '.jpg'
#一個清單,包含對應資料集圖像名稱資訊,如[000001,000007,...,000267]
self._image_index = self._load_image_set_index()
# Default to roidb handler
#self._roidb_handler = self.selective_search_roidb
#得到roi圖檔資訊,重載imdb中
self._roidb_handler = self.gt_roidb
#生成一個随機的uuid,即對于分布式資料,每個資料都有自己對應的唯一的辨別符,uuid4是根據随機數生成機制,前面随機數種子已經定義了np.random.seed(3)
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' : }
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)
#重載了imdb.py中定義,傳回圖檔所在全路徑
def image_path_at(self, i):
"""
Return the absolute path to image i in the image sequence.
"""
return self.image_path_from_index(self._image_index[i])
#image_path_at中調用,組合圖檔所在全路徑
def image_path_from_index(self, index):
"""
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):
#擷取圖檔引索
"""
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)
with open(image_set_file) as f:
#http://www.cnblogs.com/itdyb/p/5046472.html
#x.strip()就是當括号内為空就删除x開頭與結尾的('/n','/t',' ')
#如果括号内有不為空,x.strip(XX)就在x的開頭和結尾删除XX
#還有隻管開頭lstrip(),結尾rstrip()
image_index = [x.strip() for x in f.readlines()]
#傳回的image_index為一個清單,包含該資料集圖檔名稱資訊(之前做VOC資料集時候就有在對應txt中,是沒有.jpg字尾的,這是為了讓你友善修改代碼,制作自己的資料集)
return image_index
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
#由config.py可知_get_default_path傳回的是 Fsater-RCNN_TF/data/VOCdevkit+self._year
return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)
def gt_roidb(self):
#得到ROI組成的database
"""
Return the database of ground-truth regions of interest.
This function loads/saves from/to a cache file to speed up future calls.
"""
#cache_path=abs(Fsater-RCNN_TF/data/cache),self.name為voc_' + year + '_' + image_set
# 則cache_file為abs(Fsater-RCNN_TF/data/cache)/'voc_' + year + '_' + image_set+'_gt_roidb.pkl'
#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')
#加載cache_file至roidb
if os.path.exists(cache_file):
with open(cache_file, 'rb') as fid:
#b=cPickle.load(a).加載a至b
#d=cPickle.dump(c,fid, cPickle.HIGHEST_PROTOCOL).把c存到fid,一種高效的加載方式cPickle.HIGHEST_PROTOCOL,可使得節省80%空間
roidb = cPickle.load(fid)
print '{} gt roidb loaded from {}'.format(self.name, cache_file)
return roidb
#self._load_pascal_annotation(index)傳回的是該圖檔資訊dict,然後按順序存進一個list,對應圖檔資訊引索與self.image_index引索相對應
gt_roidb = [self._load_pascal_annotation(index)
for index in self.image_index]
#将gt_roidb存入臨時檔案cache_file
with open(cache_file, 'wb') as fid:
cPickle.dump(gt_roidb, fid, cPickle.HIGHEST_PROTOCOL)
print 'wrote gt roidb to {}'.format(cache_file)
#傳回gt_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) == 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) == 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[]):
boxes = raw_data[i][:, (, , , )] -
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.
"""
#定位Fsater - RCNN_TF / data / VOCdevkit +'year'/'VOC' + self._year/Annotations/000001.xml
filename = os.path.join(self._data_path, 'Annotations', index + '.xml')
#用xml.etree.ElementTree打開XML檔案
tree = ET.parse(filename)
objs = tree.findall('object')
if not self.config['use_diff']:
# Exclude the samples labeled as difficult
#xml檔案中該object有一個屬性difficult,1表示目标難以區分,0表示容易識别、
#該操作就是要吧有difficult的目标給剔除
non_diff_objs = [
obj for obj in objs if int(obj.find('difficult').text) == ]
# 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)
#初始化boxes,先建立一個shape為(num_objs, 4)的全零矩陣,num_objs為該引索圖檔中物體的個數,如有兩隻貓,則num_objs=2
boxes = np.zeros((num_objs, ), dtype=np.uint16)
#初始化gt_classes,shape為(num_objs)
gt_classes = np.zeros((num_objs), dtype=np.int32)
#overlaps(重疊),shape(num_objs, self.num_classes),self.num_classes為之前定義的所有分類的個數
overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)
# "Seg" area for pascal is just the box area
#初始化seg_areas,shape為(num_objs)
seg_areas = np.zeros((num_objs), dtype=np.float32)
# Load object bounding boxes into a data frame.
#對每一個objs中的obj進行操作
for ix, obj in enumerate(objs):
bbox = obj.find('bndbox')
# Make pixel indexes 0-based
#記錄objs的bbox值
x1 = float(bbox.find('xmin').text) -
y1 = float(bbox.find('ymin').text) -
x2 = float(bbox.find('xmax').text) -
y2 = float(bbox.find('ymax').text) -
#之前已經定義好的self._class_to_ind裡存的是{'__background__':0,'aeroplane':1.....}
#取出目前obj的name,變小寫,去除字元串頭尾 '/n','/t',' ',然後取出對應字典中的引索值,如aeroplane的cls為1
cls = self._class_to_ind[obj.find('name').text.lower().strip()]
#e.g. boxes為([貓1的四個bbox值],[貓2的四個bbox值]..)
boxes[ix, :] = [x1, y1, x2, y2]
#e.g. (1,7,10,4..)
gt_classes[ix] = cls
#e.g. 生成類似與one-hot編碼[[0,0,0,0,1,0,0,0,][0,0,0,0,1,0,0,0,]]
overlaps[ix, cls] =
#計算bbox面積
seg_areas[ix] = (x2 - x1 + ) * (y2 - y1 + )
#将overlaps稀疏矩陣壓縮
overlaps = scipy.sparse.csr_matrix(overlaps)
#總結類型:以下key的類型依次為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):
# 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[]):
f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'.
format(index, dets[k, -],
dets[k, ] + , dets[k, ] + ,
dets[k, ] + , dets[k, ] + ))
def _do_python_eval(self, output_dir = 'output'):
annopath = os.path.join(
self._devkit_path,
'VOC' + self._year,
'Annotations',
'{:s}.xml')
imagesetfile = os.path.join(
self._devkit_path,
'VOC' + self._year,
'ImageSets',
'Main',
self._image_set + '.txt')
cachedir = os.path.join(self._devkit_path, 'annotations_cache')
aps = []
# The PASCAL VOC metric changed in 2010
use_07_metric = True if int(self._year) < else False
print 'VOC07 metric? ' + ('Yes' if use_07_metric else 'No')
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
for i, cls in enumerate(self._classes):
if cls == '__background__':
continue
filename = self._get_voc_results_file_template().format(cls)
rec, prec, ap = voc_eval(
filename, annopath, imagesetfile, cls, cachedir, ovthresh=,
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()