-
Notifications
You must be signed in to change notification settings - Fork 185
/
dota-v1.5_evaluation_task1.py
304 lines (266 loc) · 10.9 KB
/
dota-v1.5_evaluation_task1.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
# --------------------------------------------------------
# dota_evaluation_task1
# Licensed under The MIT License [see LICENSE for details]
# Written by Jian Ding, based on code from Bharath Hariharan
# --------------------------------------------------------
"""
To use the code, users should to config detpath, annopath and imagesetfile
detpath is the path for 15 result files, for the format, you can refer to "http://captain.whu.edu.cn/DOTAweb/tasks.html"
search for PATH_TO_BE_CONFIGURED to config the paths
Note, the evaluation is on the large scale images
"""
import xml.etree.ElementTree as ET
import os
#import cPickle
import numpy as np
import matplotlib.pyplot as plt
import polyiou
from functools import partial
import pdb
def parse_gt(filename):
"""
:param filename: ground truth file to parse
:return: all instances in a picture
"""
objects = []
with open(filename, 'r') as f:
while True:
line = f.readline()
if line:
splitlines = line.strip().split(' ')
object_struct = {}
if (len(splitlines) < 9):
continue
object_struct['name'] = splitlines[8]
# if (len(splitlines) == 9):
# object_struct['difficult'] = 0
# elif (len(splitlines) == 10):
# object_struct['difficult'] = int(splitlines[9])
object_struct['difficult'] = 0
object_struct['bbox'] = [float(splitlines[0]),
float(splitlines[1]),
float(splitlines[2]),
float(splitlines[3]),
float(splitlines[4]),
float(splitlines[5]),
float(splitlines[6]),
float(splitlines[7])]
objects.append(object_struct)
else:
break
return objects
def voc_ap(rec, prec, use_07_metric=False):
""" ap = voc_ap(rec, prec, [use_07_metric])
Compute VOC AP given precision and recall.
If use_07_metric is true, uses the
VOC 07 11 point method (default:False).
"""
if use_07_metric:
# 11 point metric
ap = 0.
for t in np.arange(0., 1.1, 0.1):
if np.sum(rec >= t) == 0:
p = 0
else:
p = np.max(prec[rec >= t])
ap = ap + p / 11.
else:
# correct AP calculation
# first append sentinel values at the end
mrec = np.concatenate(([0.], rec, [1.]))
mpre = np.concatenate(([0.], prec, [0.]))
# compute the precision envelope
for i in range(mpre.size - 1, 0, -1):
mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])
# to calculate area under PR curve, look for points
# where X axis (recall) changes value
i = np.where(mrec[1:] != mrec[:-1])[0]
# and sum (\Delta recall) * prec
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
return ap
def voc_eval(detpath,
annopath,
imagesetfile,
classname,
# cachedir,
ovthresh=0.5,
use_07_metric=False):
"""rec, prec, ap = voc_eval(detpath,
annopath,
imagesetfile,
classname,
[ovthresh],
[use_07_metric])
Top level function that does the PASCAL VOC evaluation.
detpath: Path to detections
detpath.format(classname) should produce the detection results file.
annopath: Path to annotations
annopath.format(imagename) should be the xml annotations file.
imagesetfile: Text file containing the list of images, one image per line.
classname: Category name (duh)
cachedir: Directory for caching the annotations
[ovthresh]: Overlap threshold (default = 0.5)
[use_07_metric]: Whether to use VOC07's 11 point AP computation
(default False)
"""
# assumes detections are in detpath.format(classname)
# assumes annotations are in annopath.format(imagename)
# assumes imagesetfile is a text file with each line an image name
# cachedir caches the annotations in a pickle file
# first load gt
#if not os.path.isdir(cachedir):
# os.mkdir(cachedir)
#cachefile = os.path.join(cachedir, 'annots.pkl')
# read list of images
with open(imagesetfile, 'r') as f:
lines = f.readlines()
imagenames = [x.strip() for x in lines]
#print('imagenames: ', imagenames)
#if not os.path.isfile(cachefile):
# load annots
recs = {}
for i, imagename in enumerate(imagenames):
#print('parse_files name: ', annopath.format(imagename))
recs[imagename] = parse_gt(annopath.format(imagename))
# extract gt objects for this class
class_recs = {}
npos = 0
for imagename in imagenames:
R = [obj for obj in recs[imagename] if obj['name'] == classname]
bbox = np.array([x['bbox'] for x in R])
difficult = np.array([x['difficult'] for x in R]).astype(np.bool)
det = [False] * len(R)
npos = npos + sum(~difficult)
class_recs[imagename] = {'bbox': bbox,
'difficult': difficult,
'det': det}
# read dets from Task1* files
detfile = detpath.format(classname)
with open(detfile, 'r') as f:
lines = f.readlines()
splitlines = [x.strip().split(' ') for x in lines]
image_ids = [x[0] for x in splitlines]
confidence = np.array([float(x[1]) for x in splitlines])
#print('check confidence: ', confidence)
BB = np.array([[float(z) for z in x[2:]] for x in splitlines])
# sort by confidence
sorted_ind = np.argsort(-confidence)
sorted_scores = np.sort(-confidence)
#print('check sorted_scores: ', sorted_scores)
#print('check sorted_ind: ', sorted_ind)
## note the usage only in numpy not for list
BB = BB[sorted_ind, :]
image_ids = [image_ids[x] for x in sorted_ind]
#print('check imge_ids: ', image_ids)
#print('imge_ids len:', len(image_ids))
# go down dets and mark TPs and FPs
nd = len(image_ids)
tp = np.zeros(nd)
fp = np.zeros(nd)
for d in range(nd):
R = class_recs[image_ids[d]]
bb = BB[d, :].astype(float)
ovmax = -np.inf
BBGT = R['bbox'].astype(float)
## compute det bb with each BBGT
if BBGT.size > 0:
# compute overlaps
# intersection
# 1. calculate the overlaps between hbbs, if the iou between hbbs are 0, the iou between obbs are 0, too.
# pdb.set_trace()
BBGT_xmin = np.min(BBGT[:, 0::2], axis=1)
BBGT_ymin = np.min(BBGT[:, 1::2], axis=1)
BBGT_xmax = np.max(BBGT[:, 0::2], axis=1)
BBGT_ymax = np.max(BBGT[:, 1::2], axis=1)
bb_xmin = np.min(bb[0::2])
bb_ymin = np.min(bb[1::2])
bb_xmax = np.max(bb[0::2])
bb_ymax = np.max(bb[1::2])
ixmin = np.maximum(BBGT_xmin, bb_xmin)
iymin = np.maximum(BBGT_ymin, bb_ymin)
ixmax = np.minimum(BBGT_xmax, bb_xmax)
iymax = np.minimum(BBGT_ymax, bb_ymax)
iw = np.maximum(ixmax - ixmin + 1., 0.)
ih = np.maximum(iymax - iymin + 1., 0.)
inters = iw * ih
# union
uni = ((bb_xmax - bb_xmin + 1.) * (bb_ymax - bb_ymin + 1.) +
(BBGT_xmax - BBGT_xmin + 1.) *
(BBGT_ymax - BBGT_ymin + 1.) - inters)
overlaps = inters / uni
BBGT_keep_mask = overlaps > 0
BBGT_keep = BBGT[BBGT_keep_mask, :]
BBGT_keep_index = np.where(overlaps > 0)[0]
# pdb.set_trace()
def calcoverlaps(BBGT_keep, bb):
overlaps = []
for index, GT in enumerate(BBGT_keep):
overlap = polyiou.iou_poly(polyiou.VectorDouble(BBGT_keep[index]), polyiou.VectorDouble(bb))
overlaps.append(overlap)
return overlaps
if len(BBGT_keep) > 0:
overlaps = calcoverlaps(BBGT_keep, bb)
ovmax = np.max(overlaps)
jmax = np.argmax(overlaps)
# pdb.set_trace()
jmax = BBGT_keep_index[jmax]
if ovmax > ovthresh:
if not R['difficult'][jmax]:
if not R['det'][jmax]:
tp[d] = 1.
R['det'][jmax] = 1
else:
fp[d] = 1.
else:
fp[d] = 1.
# compute precision recall
print('check fp:', fp)
print('check tp', tp)
print('npos num:', npos)
fp = np.cumsum(fp)
tp = np.cumsum(tp)
rec = tp / float(npos)
# avoid divide by zero in case the first detection matches a difficult
# ground truth
prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)
ap = voc_ap(rec, prec, use_07_metric)
return rec, prec, ap
def main():
detpath = r'/home/dingjian/data/DOTA-v1.5/example/RoITrans/Task1_{:s}.txt'
annopath = r'/home/dingjian/code/DOAI_server2/media/DOTA15_Task1_gt/{:s}.txt'
imagesetfile = r'/home/dingjian/code/DOAI_server2/media/testset.txt'
# detpath = r'PATH_TO_BE_CONFIGURED/Task1_{:s}.txt'
# annopath = r'PATH_TO_BE_CONFIGURED/{:s}.txt' # change the directory to the path of val/labelTxt, if you want to do evaluation on the valset
# imagesetfile = r'PATH_TO_BE_CONFIGURED/valset.txt'
# For DOTA-v1.5
classnames = ['plane', 'baseball-diamond', 'bridge', 'ground-track-field', 'small-vehicle', 'large-vehicle', 'ship', 'tennis-court',
'basketball-court', 'storage-tank', 'soccer-ball-field', 'roundabout', 'harbor', 'swimming-pool', 'helicopter', 'container-crane']
# For DOTA-v1.0
# classnames = ['plane', 'baseball-diamond', 'bridge', 'ground-track-field', 'small-vehicle', 'large-vehicle', 'ship', 'tennis-court',
# 'basketball-court', 'storage-tank', 'soccer-ball-field', 'roundabout', 'harbor', 'swimming-pool', 'helicopter', ']
classaps = []
map = 0
for classname in classnames:
print('classname:', classname)
rec, prec, ap = voc_eval(detpath,
annopath,
imagesetfile,
classname,
ovthresh=0.5,
use_07_metric=True)
map = map + ap
#print('rec: ', rec, 'prec: ', prec, 'ap: ', ap)
print('ap: ', ap)
classaps.append(ap)
# umcomment to show p-r curve of each category
# plt.figure(figsize=(8,4))
# plt.xlabel('recall')
# plt.ylabel('precision')
# plt.plot(rec, prec)
# plt.show()
map = map/len(classnames)
print('map:', map)
classaps = 100*np.array(classaps)
print('classaps: ', classaps)
if __name__ == '__main__':
main()