def load_train(i):
if i % 100 == 0:
print('dataset', i, '/', len(lines))
line = lines[i]
if line[0] == 'test_cls':
prs, gts = line[1:]
prs, gts = json.loads(prs), json.loads(gts)
image = cv2.imread(
os.path.join(settings.TEST_IMAGE_DIR, prs['file_name']))
assert image.shape == (prs['height'], prs['width'], 3)
for pr, gt in zip(prs['proposals'], gts['ground_truth']):
cropped = predictions2html.crop(image, pr['adjusted_bbox'],
64)
all[i].append([cropped, gt['attributes']])
else:
anno = json.loads(line[1].strip())
image = cv2.imread(
os.path.join(
settings.TRAINVAL_IMAGE_DIR if line[0]
in {'train', 'val'} else settings.TEST_IMAGE_DIR,
anno['file_name']))
assert image.shape == (anno['height'], anno['width'], 3)
for char in anno_tools.each_char(anno):
if not char['is_chinese']:
continue
cropped = predictions2html.crop(image,
char['adjusted_bbox'], 64)
all[i].append([cropped, char['attributes']])
def get_polygons():
lines = []
with open(settings.TRAIN) as f:
lines += [('train', s) for s in f.read().splitlines()]
with open(settings.VAL) as f:
lines += [('val', s) for s in f.read().splitlines()]
with open(settings.TEST_CLASSIFICATION) as f1, open(
settings.TEST_CLASSIFICATION_GT) as f2:
prs = f1.read().splitlines()
gts = f2.read().splitlines()
lines += [('test_cls', pr, gt) for pr, gt in zip(prs, gts)]
with open(settings.TEST_DETECTION_GT) as f:
lines += [('test_det', s) for s in f.read().splitlines()]
polygons = []
for i, line in enumerate(lines):
if line[0] == 'test_cls':
prs = line[1]
prs = json.loads(prs.strip())
for pr in prs['proposals']:
polygons.append(pr['polygon'])
else:
anno = json.loads(line[1].strip())
for char in anno_tools.each_char(anno):
if not char['is_chinese']:
continue
polygons.append(char['polygon'])
return polygons
def main():
# load from downloads
with open('../data/annotations/downloads/info.json') as f:
full_data_list = json.load(f)
with open('../data/annotations/downloads/val.jsonl') as f:
val = f.read().splitlines()
# make infomation of data list
data_list = {
'train': full_data_list['train'],
'val': [],
'test_cls': full_data_list['val'],
'test_det': full_data_list['val'],
}
with open(settings.DATA_LIST, 'w') as f:
json.dump(data_list, f, indent=2)
# copy training set
shutil.copy('../data/annotations/downloads/train.jsonl', settings.TRAIN)
# create empty validation set
with open(settings.VAL, 'w') as f:
pass
# create testing set for classification
with open(settings.TEST_CLASSIFICATION,
'w') as f, open(settings.TEST_CLASSIFICATION_GT, 'w') as fgt:
for line in val:
anno = json.loads(line.strip())
proposals = []
gt = []
for char in anno_tools.each_char(anno):
if not char['is_chinese']:
continue
proposals.append({
'adjusted_bbox': char['adjusted_bbox'],
'polygon': char['polygon']
})
gt.append({
'text': char['text'],
'attributes': char['attributes'],
'size': char['adjusted_bbox'][-2:]
})
anno.pop('annotations')
anno.pop('ignore')
anno['proposals'] = proposals
f.write(common_tools.to_jsonl(anno))
f.write('\n')
anno.pop('proposals')
anno['ground_truth'] = gt
fgt.write(common_tools.to_jsonl(anno))
fgt.write('\n')
# create testing set for detection
shutil.copy('../data/annotations/downloads/val.jsonl',
settings.TEST_DETECTION_GT)
def load_train(i):
if i % 100 == 0:
print('trainval', i, '/', len(lines))
anno = json.loads(lines[i].strip())
image = misc.imread(
os.path.join(settings.TRAINVAL_IMAGE_DIR, anno['file_name']))
assert image.shape == (anno['height'], anno['width'], 3)
for char in anno_tools.each_char(anno):
if not char['is_chinese']:
continue
cropped = crop(image, char['adjusted_bbox'])
train[i].append([cropped, char['text']])
def crop_once(line, write_images):
anno = json.loads(line.strip())
image_id = anno['image_id']
all = []
for char in anno_tools.each_char(anno):
if not char['is_chinese']:
continue
cate_id = text2cate[char['text']]
if cate_id >= settings.NUM_CHAR_CATES:
cate_id = settings.NUM_CHAR_CATES
all.append((char['adjusted_bbox'], cate_id))
if write_images:
image = cv2.imread(
os.path.join(settings.TRAINVAL_IMAGE_DIR, anno['file_name']))
assert image.shape == imshape
for o in anno['ignore']:
poly = (np.array(o['polygon'])).astype(np.int32)
cv2.fillConvexPoly(image, poly, (128, 128, 128))
cropped_list = list()
for o in darknet_tools.get_crop_bboxes(imshape, cropshape,
cropoverlap):
xlo = o['xlo']
xhi = xlo + cropshape[1]
ylo = o['ylo']
yhi = ylo + cropshape[0]
labels = []
for bbox, cate_id in all:
x, y, w, h = bbox
if x > xhi or x + w < xlo or y > yhi or y + h < ylo:
continue
bbox = ((x + w / 2 - xlo) / cropshape[1],
(y + h / 2 - ylo) / cropshape[0], w / cropshape[1],
h / cropshape[0])
if 0.5 < in_image_ratio(bbox):
labels.append((bbox, cate_id))
if 0 < len(labels):
basename = '{}_{}'.format(image_id, o['name'])
cropped_file_name = os.path.join(settings.TRAINVAL_CROPPED_DIR,
'{}.jpg'.format(basename))
cropped_xml_name = os.path.join(settings.TRAINVAL_CROPPED_DIR,
'{}.xml'.format(basename))
cropped_list.append('{} {}'.format(cropped_file_name,
cropped_xml_name))
if write_images:
cropped = image[ylo:yhi, xlo:xhi]
cv2.imwrite(cropped_file_name, cropped)
with open(
os.path.join(settings.TRAINVAL_CROPPED_DIR,
'{}.xml'.format(basename)), 'w') as f:
write_xml(labels, cropshape, f)
return cropped_list
def crop_no_concat():
assert six.PY3
random.seed(0)
belongs = defaultdict(list)
with open(settings.TRAIN) as f:
lines = f.read().splitlines()
with open(settings.VAL) as f:
lines += f.read().splitlines()
for line in lines:
anno = json.loads(line.strip())
i = 0
for char in anno_tools.each_char(anno):
if not char['is_chinese']:
continue
for attr in settings.ATTRIBUTES:
if attr in char['attributes']:
belongs[attr].append((anno['image_id'], anno['file_name'],
char['adjusted_bbox'], i))
else:
belongs['not-{}'.format(attr)].append(
(anno['image_id'], anno['file_name'],
char['adjusted_bbox'], i))
i += 1
for attr, imgset in sorted(belongs.items()):
imgset = random.sample(imgset, 200)
root = os.path.join(settings.ATTR_SAMPLE_DIR, attr)
resized_root = os.path.join(settings.ATTR_SAMPLE_DIR,
'{}-resized'.format(attr))
if not os.path.isdir(root):
os.makedirs(root)
if not os.path.isdir(resized_root):
os.makedirs(resized_root)
for i, (image_id, file_name, bbox, idx_in_img) in enumerate(imgset):
if i % 100 == 0:
print(attr, i, '/', len(imgset))
image = cv2.imread(
os.path.join(settings.TRAINVAL_IMAGE_DIR, file_name))
cropped_file_path = os.path.join(
root, '{}_{}.png'.format(image_id, idx_in_img))
resized_file_path = os.path.join(
resized_root, '{}_{}.png'.format(image_id, idx_in_img))
cropped = predictions2html.crop(image, bbox, float('inf'))
resized = cv2.resize(cropped, (32, 32))
cv2.imwrite(cropped_file_path, cropped)
cv2.imwrite(resized_file_path, resized)
def gt2array(gt, draw_ignore):
color = '#f00'
color_ignore = '#ff0'
a = list()
for char in anno_tools.each_char(gt):
if char['is_chinese']:
a.append({
'bbox': char['adjusted_bbox'],
'text': char['text'],
'color': color
})
if draw_ignore:
for char in gt['ignore']:
a.append({
'bbox': char['bbox'],
'text': '',
'color': color_ignore
})
return a
def gt2array(gt):
color = '#0f0'
a = list()
for char in anno_tools.each_char(gt):
if char['is_chinese']:
a.append({
'polygon': char['polygon'],
'text': char['text'],
'color': color,
'fontsize': 10
})
for char in gt['ignore']:
a.append({
'polygon': char['polygon'],
'text': '',
'color': '#ff0',
'fontsize': 10
})
return a
def main():
counts = defaultdict(int)
with open(settings.TRAIN) as f, open(settings.VAL) as f2:
for line in f.read().splitlines() + f2.read().splitlines():
anno = json.loads(line.strip())
for char in anno_tools.each_char(anno):
if char['is_chinese']:
text = char['text']
assert 1 == len(text)
counts[text] += 1
cates = [{
'text': k,
'trainval': v,
} for k, v in counts.items()]
cates.sort(key=lambda o: (-o['trainval'], o['text']))
for i, o in enumerate(cates):
o['cate_id'] = i
with codecs.open(settings.CATES, 'w', 'utf-8') as f:
json.dump(cates,
f,
ensure_ascii=False,
allow_nan=False,
indent=2,
sort_keys=True)
def dt2array(dtobj, gtobj, draw_ignore, draw_proposal):
iou_thresh = settings.IOU_THRESH
charset = set()
proposal = False
def in_size(_):
return True
dt = dtobj['detections']
dt.sort(
key=lambda o: -o['score']
) # sort must be stable, otherwise mAP will be slightly different
dt = [(o['bbox'], o.get('text'), o['score']) for o in dt]
ig = [(o['bbox'], None) for o in gtobj['ignore']]
gt = []
for char in anno_tools.each_char(gtobj):
if char['is_chinese']:
charset.add(char['text'])
gt.append(
(char['adjusted_bbox'], char['text'], char['attributes']))
dt_matches = [[] for i in range(len(dt))]
dt_ig = [False] * len(dt)
for i_dt, dtchar in enumerate(dt):
for i_gt, gtchar in enumerate(gt):
if proposal or dtchar[1] == gtchar[1]:
miou = eval_tools.iou(dtchar[0], gtchar[0])
if miou > iou_thresh:
dt_matches[i_dt].append((i_gt, miou))
for igchar in ig:
miou = eval_tools.a_in_b(dtchar[0], igchar[0])
if miou > iou_thresh:
dt_ig[i_dt] = True
for matches in dt_matches:
matches.sort(
key=lambda t: -t[1]
) # sort must be stable, otherwise you shoule use key=lambda t: (-t[1], t[0])
dt_matched = [
0 if in_size(o[0]) and False == b else 2
for o, b in zip(dt, dt_ig)
]
gt_taken = [(0, None) if in_size(o[0]) else (2, None) for o in gt]
for i_dt, matches in enumerate(dt_matches):
for i_gt, _ in matches:
if 1 != dt_matched[i_dt] and 1 != gt_taken[i_gt][0]:
if 0 == gt_taken[i_gt][0]:
dt_matched[i_dt] = 1
gt_taken[i_gt] = (1, i_dt)
else:
dt_matched[i_dt] = 2
a = list()
minscore = 1.
colormap = {0: '#ff0', 1: '#0f0', 2: '#0ff'}
for i in range(len(dt)):
if len(a) >= len(gt):
break
bbox, text, score = dt[i]
taken = dt_matched[i]
if 2 != taken or draw_ignore:
flag = True
for o in a:
if settings.IOU_THRESH < eval_tools.a_in_b(
bbox, o['bbox']
) or settings.IOU_THRESH < eval_tools.a_in_b(
o['bbox'], bbox):
flag = False
if flag:
a.append({
'bbox': bbox,
'text': text or '■',
'color': colormap[taken]
})
minscore = score
if draw_proposal:
for o in sorted(dtobj['proposals'], key=lambda o: -o['score']):
bbox, score = o['bbox'], o['score']
if score >= minscore:
s = 0
for igbbox, _ in ig:
s += eval_tools.a_in_b(bbox, igbbox)
for o in a:
s += max(eval_tools.a_in_b(o['bbox'], bbox),
eval_tools.a_in_b(bbox, o['bbox']))
if s <= settings.IOU_THRESH:
a.append({'bbox': bbox, 'text': '', 'color': '#00f'})
return list(reversed(a))
def main():
allowed_filename = get_allowed_filename()
basename2cnt = dict()
imgid2anno = dict()
with codecs.open(settings.OVERALL_ANNOTATIONS, 'r', 'utf-8') as f:
for line in f:
image_anno = json.loads(line.strip())
image_id = image_anno['image_id']
if image_id[:3] == '204':
logo_bbox = [810., 1800., 460., 100.]
image_anno['ignore'].append({
'bbox': logo_bbox,
'polygon': bbox2poly(logo_bbox),
})
else:
logo_bbox = None
for i, blk in enumerate(image_anno['annotations']):
image_anno['annotations'][i] = list(
filter(
is_legal_char(
(image_anno['height'], image_anno['width'], 3),
logo_bbox), blk))
image_anno['annotations'] = list(
filter(lambda a: a, image_anno['annotations']))
direction = image_id[0]
onew = image_id[1:]
oold = mapper.new2old[onew]
complete_basename = '{}.{}'.format(oold, direction)
if image_id[
1:3] != '04' and complete_basename not in allowed_filename:
continue
is_chinese = 0
is_not_chinese = 0
for char in anno_tools.each_char(image_anno):
if char['is_chinese']:
is_chinese += 1
else:
is_not_chinese += 1
if 0 == is_chinese:
continue
basename2cnt[complete_basename] = [is_chinese, is_not_chinese]
imgid2anno[image_id] = image_anno
streets = []
current_street = []
def feature(basename):
assert 25 == len(basename)
cityid = basename[:4]
streetid = basename[4:8]
dateid = basename[8:14]
timeid = basename[14:23]
direction = basename[-1]
return (cityid, streetid, dateid, timeid, direction)
def like(n1, n2):
f1, f2 = feature(n1), feature(n2)
return (f1[0], f1[1], f1[2]) == (f2[0], f2[1], f2[2])
for i, basename in enumerate(sorted(basename2cnt.keys())):
if i == 0 or like(last_basename, basename):
current_street.append(basename)
else:
streets.append(current_street)
current_street = [basename]
last_basename = basename
streets.append(current_street)
def count_chinese(a):
return sum([basename2cnt[basename][0] for basename in a])
np.random.seed(0)
train = []
tests = [[], [], []]
requires = [101000, 101000, 50500]
basenames = sorted(mapper.old2new.keys())
for i, st in enumerate(streets):
ntest = 100
nval = 50
ntrainval = 1200
ninterval = 5
if ntest * 2 + ninterval + ntrainval < len(st):
while 0 < len(st):
j = np.random.randint(0, 2)
tests[j] += st[0:ntest]
tests[1 - j] += st[ntest:ntest * 2]
lastname = st[ntest * 2 - 1].split('.')[0]
lastpos = bisect.bisect(basenames, lastname) - 1
assert basenames[lastpos] == lastname
st = st[ntest * 2:]
j = 0
while True:
name = st[j].split('.')[0]
pos = bisect.bisect(basenames, name) - 1
assert basenames[pos] == name
if pos - lastpos <= ninterval:
j += 1
else:
break
st = st[j:]
hi = ntrainval
if len(st) < ntrainval * (math.sqrt(5) +
1) / 2 + ntest * 2 + ninterval * 2:
hi = len(st)
j = np.random.randint(0, 2)
train += st[j * nval:hi - nval + j * nval]
tests[2] += st[0:j * nval] + st[hi - nval + j * nval:hi]
lastname = st[hi - 1].split('.')[0]
st = st[hi:]
if 0 < len(st):
lastpos = bisect.bisect(basenames, lastname) - 1
j = 0
while True:
name = st[j].split('.')[0]
pos = bisect.bisect(basenames, name) - 1
assert (basenames[pos] == name)
if pos - lastpos <= ninterval:
j += 1
else:
break
st = st[j:]
streets[i] = []
counts = [count_chinese(test) for test in tests]
while (np.array(counts) < np.array(requires)).any():
i = np.random.randint(0, len(streets))
j = np.random.randint(0, len(requires))
if counts[j] >= requires[j]:
continue
st = streets[i]
if 300 < len(st):
continue
tests[j] += streets.pop(i)
counts[j] = count_chinese(tests[j])
for st in streets:
train += st
print('train', len(train), count_chinese(train))
print('val', len(tests[2]), count_chinese(tests[2]))
print('test_1', len(tests[0]), count_chinese(tests[0]))
print('test_2', len(tests[1]), count_chinese(tests[1]))
def basename2imgid(bn):
a, direction = bn.split('.')
return '{}{}'.format(direction, mapper.old2new[a])
train = sorted(map(basename2imgid, train))
val = sorted(map(basename2imgid, tests[2]))
test_1 = sorted(map(basename2imgid, tests[0]))
test_2 = sorted(map(basename2imgid, tests[1]))
def toinfo(anno):
keys = list(anno.keys())
keys.remove('annotations')
keys.remove('ignore')
return {k: anno[k] for k in keys}
with open(settings.DATA_LIST, 'w') as f:
def g(ds):
return [toinfo(imgid2anno[imgid]) for imgid in ds]
r = {
'train': g(train),
'val': g(val),
'test_cls': g(test_1),
'test_det': g(test_2)
}
json.dump(r,
f,
ensure_ascii=True,
allow_nan=False,
indent=2,
sort_keys=True)
with open(settings.TRAIN, 'w') as f:
for imgid in train:
f.write(common_tools.to_jsonl(imgid2anno[imgid]))
f.write('\n')
with open(settings.VAL, 'w') as f:
for imgid in val:
f.write(common_tools.to_jsonl(imgid2anno[imgid]))
f.write('\n')
with open(settings.TEST_CLASSIFICATION,
'w') as f, open(settings.TEST_CLASSIFICATION_GT, 'w') as fgt:
for imgid in test_1:
anno = imgid2anno[imgid]
proposals = []
gt = []
for char in anno_tools.each_char(anno):
if not char['is_chinese']:
continue
proposals.append({
'adjusted_bbox': char['adjusted_bbox'],
'polygon': char['polygon']
})
gt.append({
'text': char['text'],
'attributes': char['attributes'],
'size': char['adjusted_bbox'][-2:]
})
anno.pop('annotations')
anno.pop('ignore')
anno['proposals'] = proposals
f.write(common_tools.to_jsonl(anno))
f.write('\n')
anno.pop('proposals')
anno['ground_truth'] = gt
fgt.write(common_tools.to_jsonl(anno))
fgt.write('\n')
with open(settings.TEST_DETECTION_GT, 'w') as f:
for imgid in test_2:
f.write(common_tools.to_jsonl(imgid2anno[imgid]))
f.write('\n')
def main():
all = defaultdict(int)
n = 0
with open(settings.TRAIN) as f1, open(settings.VAL) as f2:
for line in f1.read().splitlines() + f2.read().splitlines():
anno = json.loads(line.strip())
for char in anno_tools.each_char(anno):
if char['is_chinese']:
k = 0
n += 1
for attr in char['attributes']:
k |= 2**settings.ATTRIBUTES.index(attr)
for szname, (lo, hi) in settings.SIZE_RANGES:
if lo <= max(char['adjusted_bbox'][2:]) < hi:
all['trainval', szname, k] += 1
with open(settings.TEST_CLASSIFICATION_GT) as f2:
for line in f2:
gts = json.loads(line.strip())
for char in gts['ground_truth']:
k = 0
for attr in char['attributes']:
k |= 2**settings.ATTRIBUTES.index(attr)
for szname, (lo, hi) in settings.SIZE_RANGES:
if lo <= max(char['size']) < hi:
all['test', szname, k] += 1
with open(settings.TEST_DETECTION_GT) as f:
for line in f:
anno = json.loads(line.strip())
for char in anno_tools.each_char(anno):
if char['is_chinese']:
k = 0
for attr in char['attributes']:
k |= 2**settings.ATTRIBUTES.index(attr)
for szname, (lo, hi) in settings.SIZE_RANGES:
if lo <= max(char['adjusted_bbox'][2:]) < hi:
all['test', szname, k] += 1
def check(k, attr_id):
if attr_id < len(settings.ATTRIBUTES):
return int(k) & 2**attr_id
else:
return 0 == int(k) & 2**(attr_id - len(settings.ATTRIBUTES))
def trans(attr_id):
if attr_id < len(settings.ATTRIBUTES):
return settings.ATTRIBUTES[attr_id]
else:
return r'$\sim${}'.format(
settings.ATTRIBUTES[attr_id - len(settings.ATTRIBUTES)])
for i in range(2 * len(settings.ATTRIBUTES) - 1):
for j in range(i + 1, 2 * len(settings.ATTRIBUTES)):
if j == i + len(settings.ATTRIBUTES):
continue
s = r'{}\!\!\!\!\! & \& & \!\!\!\!\!{}'.format(trans(i), trans(j))
for szname, (lo, hi) in settings.SIZE_RANGES:
n_train = n_test = 0
for k, v in all.items():
if check(k[2], i) and check(k[2], j):
if ('trainval', szname) == k[:2]:
n_train += v
if ('test', szname) == k[:2]:
n_test += v
s += ' & {} / {}'.format(
n_train, '{:5d}'.format(n_test).replace(' ', r'\,\,\,'))
s += r' \\'
print(s)
def main():
most_freq = defaultdict(lambda: {'trainval': 0, 'test': 0})
num_char = defaultdict(lambda: {'trainval': 0, 'test': 0})
num_uniq_char = defaultdict(lambda: {'trainval': 0, 'test': 0})
num_image = {'trainval': 0, 'test': 0}
sum_chinese = {'trainval': 0, 'test': 0}
sum_not_chinese = {'trainval': 0, 'test': 0}
sum_ignore = {'trainval': 0, 'test': 0}
longsizes = {'trainval': list(), 'test': list()}
attrs = {
szname: {attr: 0
for attr in settings.ATTRIBUTES + ['__all__']}
for szname, _ in settings.SIZE_RANGES
}
with open(settings.TRAIN) as f, open(settings.VAL) as f2:
for line in f.read().splitlines() + f2.read().splitlines():
anno = json.loads(line.strip())
num = 0
uniq = set()
for char in anno_tools.each_char(anno):
if char['is_chinese']:
most_freq[char['text']]['trainval'] += 1
num += 1
uniq.add(char['text'])
sum_chinese['trainval'] += 1
longsize = max(char['adjusted_bbox'][2],
char['adjusted_bbox'][3])
longsizes['trainval'].append(longsize)
for szname, szrange in settings.SIZE_RANGES:
if szrange[0] <= longsize < szrange[1]:
for attr in char['attributes']:
attrs[szname][attr] += 1
attrs[szname]['__all__'] += 1
else:
sum_not_chinese['trainval'] += 1
assert 0 < len(uniq)
num_char[num]['trainval'] += 1
num_uniq_char[len(uniq)]['trainval'] += 1
num_image['trainval'] += 1
sum_ignore['trainval'] += len(anno['ignore'])
with open(settings.TEST_CLASSIFICATION_GT) as f:
for line in f:
gt = json.loads(line.strip())['ground_truth']
num = 0
uniq = set()
for char in gt:
most_freq[char['text']]['test'] += 1
num += 1
uniq.add(char['text'])
sum_chinese['test'] += 1
longsize = max(*char['size'])
longsizes['test'].append(longsize)
for szname, szrange in settings.SIZE_RANGES:
if szrange[0] <= longsize < szrange[1]:
for attr in char['attributes']:
attrs[szname][attr] += 1
attrs[szname]['__all__'] += 1
assert 0 < len(uniq)
num_char[num]['test'] += 1
num_uniq_char[len(uniq)]['test'] += 1
num_image['test'] += 1
with open(settings.TEST_DETECTION_GT) as f:
for line in f:
anno = json.loads(line.strip())
num = 0
uniq = set()
for char in anno_tools.each_char(anno):
if char['is_chinese']:
most_freq[char['text']]['test'] += 1
num += 1
uniq.add(char['text'])
sum_chinese['test'] += 1
longsizes['test'].append(
max(char['adjusted_bbox'][2],
char['adjusted_bbox'][3]))
for szname, szrange in settings.SIZE_RANGES:
if szrange[0] <= longsize < szrange[1]:
for attr in char['attributes']:
attrs[szname][attr] += 1
attrs[szname]['__all__'] += 1
else:
sum_not_chinese['test'] += 1
assert 0 < len(uniq)
num_char[num]['test'] += 1
num_uniq_char[len(uniq)]['test'] += 1
num_image['test'] += 1
sum_ignore['test'] += len(anno['ignore'])
most_freq = [{
'text': k,
'trainval': v['trainval'],
'test': v['test'],
} for k, v in most_freq.items()]
most_freq.sort(key=lambda o: (-o['trainval'] - o['test'], o['text']))
print('10_most_frequent_characters')
for i, o in enumerate(most_freq[:10]):
print(i + 1, o['text'], o['trainval'], o['test'])
print('over_all')
print('uniq_chinese', len(most_freq))
print('num_image', num_image['trainval'], num_image['test'])
print('sum_chinese', sum_chinese['trainval'], sum_chinese['test'])
print('sum_not_chinese', sum_not_chinese['trainval'],
sum_not_chinese['test'])
print('sum_ignore', sum_ignore['trainval'], sum_ignore['test'])
with codecs.open(settings.STAT_FREQUENCY, 'w', 'utf-8') as f:
json.dump(most_freq, f, ensure_ascii=False, indent=2)
# most_freq
meta = most_freq[:50]
data = [
[
{
'legend': 'training set',
'data': [o['trainval'] for o in meta],
},
{
'legend': 'testing set',
'data': [o['test'] for o in meta],
},
],
]
labels = [o['text'] for o in meta]
with plt.style.context({
'figure.subplot.left': .06,
'figure.subplot.right': .98,
'figure.subplot.top': .96,
'pdf.fonttype': 42,
}):
plt.figure(figsize=(10, 3))
plt.xlim((0, len(labels) + 1))
plt.grid(which='major', axis='y', linestyle='dotted')
plot_tools.draw_bar(data, labels, xticks_font_fname=get_chinese_ttf())
plt.savefig(os.path.join(settings.PLOTS_DIR, 'stat_most_freq.pdf'))
plt.close()
# num_char
meta = [num_char[i] for i in range(1, 61)]
data = [
[
{
'legend': 'training set',
'data': [o['trainval'] for o in meta],
},
{
'legend': 'testing set',
'data': [o['test'] for o in meta],
},
],
]
labels = [i + 1 if (i + 1) % 10 == 0 else None for i, _ in enumerate(meta)]
with plt.style.context({
'figure.subplot.left': .14,
'figure.subplot.right': .96,
'figure.subplot.bottom': .16,
'figure.subplot.top': .96,
'pdf.fonttype': 42,
}):
plt.figure(figsize=(5, 3))
plt.xlim((0, len(labels) + 1))
plt.grid(which='major', axis='y', linestyle='dotted')
plot_tools.draw_bar(data, labels)
plt.xlabel('number of character instances')
plt.ylabel('number of images')
plt.savefig(os.path.join(settings.PLOTS_DIR, 'stat_num_char.pdf'))
plt.close()
# num_uniq_char
meta = [num_uniq_char[i] for i in range(1, 61)]
data = [
[
{
'legend': 'training set',
'data': [o['trainval'] for o in meta],
},
{
'legend': 'testing set',
'data': [o['test'] for o in meta],
},
],
]
labels = [i + 1 if (i + 1) % 10 == 0 else None for i, _ in enumerate(meta)]
with plt.style.context({
'figure.subplot.left': .14,
'figure.subplot.right': .96,
'figure.subplot.bottom': .16,
'figure.subplot.top': .96,
'pdf.fonttype': 42,
}):
plt.figure(figsize=(5, 3))
plt.xlim((0, len(labels) + 1))
plt.grid(which='major', axis='y', linestyle='dotted')
plot_tools.draw_bar(data, labels)
plt.xlabel('number of character categories')
plt.ylabel('number of images')
plt.savefig(os.path.join(settings.PLOTS_DIR, 'stat_num_uniq_char.pdf'))
plt.close()
# instance size
longsizes['trainval'].sort()
longsizes['test'].sort()
ranges = list(range(0, 65, 8))
data = [
[
{
'legend':
'training set',
'data': [
bisect.bisect_left(longsizes['trainval'], hi) -
bisect.bisect_left(longsizes['trainval'], lo)
for lo, hi in zip(ranges, ranges[1:] + [float('inf')])
],
},
{
'legend':
'testing set',
'data': [
bisect.bisect_left(longsizes['test'], hi) -
bisect.bisect_left(longsizes['test'], lo)
for lo, hi in zip(ranges, ranges[1:] + [float('inf')])
],
},
],
]
labels = [
'{}-{}'.format(lo, hi) for lo, hi in zip(ranges, ranges[1:] + [''])
]
with plt.style.context({
'figure.subplot.left': .12,
'figure.subplot.right': .96,
'figure.subplot.bottom': .10,
'figure.subplot.top': .96,
'pdf.fonttype': 42,
}):
plt.figure(figsize=(6, 3))
plt.xlim((0, len(labels) + 1))
plt.grid(which='major', axis='y', linestyle='dotted')
plot_tools.draw_bar(data, labels)
plt.savefig(os.path.join(settings.PLOTS_DIR, 'stat_instance_size.pdf'))
plt.close()
# attributes percentage
data = [[{
'legend':
szname,
'data': [
attrs[szname][attr] / attrs[szname]['__all__'] * 100
for attr in settings.ATTRIBUTES
],
}] for szname, szrange in settings.SIZE_RANGES]
labels = settings.ATTRIBUTES
with plt.style.context({
'figure.subplot.left': .12,
'figure.subplot.right': .96,
'figure.subplot.bottom': .10,
'figure.subplot.top': .96,
'pdf.fonttype': 42,
}):
plt.figure(figsize=(6, 3))
plt.xlim((.3, .7 + len(labels)))
plt.grid(which='major', axis='y', linestyle='dotted')
plt.gca().yaxis.set_major_formatter(plt.FuncFormatter(
'{:.0f}%'.format))
plot_tools.draw_bar(data, labels, width=.18)
plt.savefig(os.path.join(settings.PLOTS_DIR, 'stat_attributes.pdf'))
plt.close()
# sys.path.append('C:\\Users\\flavi\\PycharmProjects\\ctw-traffic-signs')
import settings
from pythonapi import anno_tools
with open(settings.TRAIN_AUGMENTED) as f:
lines = f.readlines()
for line in lines:
anno = json.loads(line)
if anno['image_id'] == "0500223":
to_show = anno
break
path = os.path.join(settings.TRAINVAL_AUGMENTED_DIR,
to_show['image_id'] + '.png')
assert os.path.exists(path), 'file not exists: {}'.format(path)
img = cv2.imread(path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
plt.figure(figsize=(16, 16))
ax = plt.gca()
plt.imshow(img)
for instance in anno_tools.each_char(anno):
color = (0, 1, 0) if instance['is_chinese'] else (1, 0, 0)
ax.add_patch(patches.Polygon(instance['polygon'], fill=False, color=color))
'''
for ignore in anno['ignore']:
color = (1, 1, 0)
ax.add_patch(patches.Polygon(ignore['polygon'], fill=False, color=color))
'''
plt.show()
